Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1794 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 12.5280. Min Range: -12.5280
Max Act: 12.5280. Min Act: -0.1700
Data Index: 7968887 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5280. Min Range: -12.5280
Max Act: 12.4655. Min Act: -0.1700
Data Index: 7095970 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5280. Min Range: -12.5280
Max Act: 12.2780. Min Act: -0.1700
Data Index: 2144167 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5280. Min Range: -12.5280
Max Act: 12.2780. Min Act: -0.1700
Data Index: 2433648 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5280. Min Range: -12.5280
Max Act: 12.1530. Min Act: -0.1700
Data Index: 2395520 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5280. Min Range: -12.5280
Max Act: 12.0280. Min Act: -0.1700
Data Index: 6206625 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5280. Min Range: -12.5280
Max Act: 12.0280. Min Act: -0.1700
Data Index: 7776145 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5280. Min Range: -12.5280
Max Act: 12.0280. Min Act: -0.1700
Data Index: 3493593 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5280. Min Range: -12.5280
Max Act: 12.0280. Min Act: -0.1700
Data Index: 6404517 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5280. Min Range: -12.5280
Max Act: 11.9655. Min Act: -0.1700
Data Index: 4768920 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5280. Min Range: -12.5280
Max Act: 12.0280. Min Act: -0.1700
Data Index: 127564 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5280. Min Range: -12.5280
Max Act: 12.0280. Min Act: -0.1700
Data Index: 5249188 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5280. Min Range: -12.5280
Max Act: 11.9655. Min Act: -0.1700
Data Index: 6597730 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5280. Min Range: -12.5280
Max Act: 11.9030. Min Act: -0.1700
Data Index: 3803358 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5280. Min Range: -12.5280
Max Act: 11.9030. Min Act: -0.1700
Data Index: 744101 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5280. Min Range: -12.5280
Max Act: 11.9030. Min Act: -0.1700
Data Index: 4220083 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5280. Min Range: -12.5280
Max Act: 11.9030. Min Act: -0.1700
Data Index: 4445421 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5280. Min Range: -12.5280
Max Act: 11.9655. Min Act: -0.1700
Data Index: 202403 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5280. Min Range: -12.5280
Max Act: 11.9030. Min Act: -0.1700
Data Index: 7736166 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5280. Min Range: -12.5280
Max Act: 11.9030. Min Act: -0.1700
Data Index: 2296804 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19