Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2629 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3280. Min Range: -6.3280
Max Act: 6.3280. Min Act: -0.1700
Data Index: 6934450 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3280. Min Range: -6.3280
Max Act: 5.8593. Min Act: -0.1700
Data Index: 4665873 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3280. Min Range: -6.3280
Max Act: 5.8593. Min Act: -0.1700
Data Index: 7675860 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3280. Min Range: -6.3280
Max Act: 5.8593. Min Act: -0.1700
Data Index: 7631330 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3280. Min Range: -6.3280
Max Act: 5.8593. Min Act: -0.1700
Data Index: 1401236 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3280. Min Range: -6.3280
Max Act: 5.7655. Min Act: -0.1700
Data Index: 7470588 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3280. Min Range: -6.3280
Max Act: 5.7030. Min Act: -0.1700
Data Index: 8157257 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3280. Min Range: -6.3280
Max Act: 5.6718. Min Act: -0.1700
Data Index: 2821365 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3280. Min Range: -6.3280
Max Act: 5.6405. Min Act: -0.1700
Data Index: 5140872 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3280. Min Range: -6.3280
Max Act: 5.6405. Min Act: -0.1700
Data Index: 1498891 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3280. Min Range: -6.3280
Max Act: 5.6405. Min Act: -0.1700
Data Index: 6034082 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3280. Min Range: -6.3280
Max Act: 5.6093. Min Act: -0.1700
Data Index: 1666491 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3280. Min Range: -6.3280
Max Act: 5.5780. Min Act: -0.1700
Data Index: 518700 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3280. Min Range: -6.3280
Max Act: 5.5780. Min Act: -0.1700
Data Index: 4393500 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3280. Min Range: -6.3280
Max Act: 5.5780. Min Act: -0.1700
Data Index: 2151218 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3280. Min Range: -6.3280
Max Act: 5.6093. Min Act: -0.1700
Data Index: 4861557 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3280. Min Range: -6.3280
Max Act: 5.5780. Min Act: -0.1700
Data Index: 8678340 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3280. Min Range: -6.3280
Max Act: 5.5468. Min Act: -0.1700
Data Index: 7347993 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3280. Min Range: -6.3280
Max Act: 5.5468. Min Act: -0.1700
Data Index: 528586 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3280. Min Range: -6.3280
Max Act: 5.5468. Min Act: -0.1700
Data Index: 1042007 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19