Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2608 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.4067. Min Act: -0.1700
Data Index: 725415 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.4067. Min Act: -0.1700
Data Index: 4855272 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.4067. Min Act: -0.1700
Data Index: 4618272 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.3441. Min Act: -0.1700
Data Index: 7242670 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.3441. Min Act: -0.1700
Data Index: 8669096 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.3441. Min Act: -0.1700
Data Index: 6478735 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.3129. Min Act: -0.1700
Data Index: 7150895 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.2816. Min Act: -0.1700
Data Index: 5558637 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.3129. Min Act: -0.1700
Data Index: 7212633 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.2504. Min Act: -0.1700
Data Index: 1368804 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.2504. Min Act: -0.1700
Data Index: 3713717 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.2504. Min Act: -0.1700
Data Index: 6865794 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.1879. Min Act: -0.1700
Data Index: 2601423 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.2191. Min Act: -0.1700
Data Index: 6406735 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.2191. Min Act: -0.1700
Data Index: 6853470 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.1879. Min Act: -0.1700
Data Index: 4120798 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.1879. Min Act: -0.1700
Data Index: 4529681 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.1566. Min Act: -0.1700
Data Index: 2107620 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.1879. Min Act: -0.1700
Data Index: 6386648 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4067. Min Range: -4.4067
Max Act: 4.1254. Min Act: -0.1700
Data Index: 3443650 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19