Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3986 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.4465. Min Act: -0.1700
Data Index: 3943081 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.4151. Min Act: -0.1700
Data Index: 8154202 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3838. Min Act: -0.1700
Data Index: 2636371 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3995. Min Act: -0.1700
Data Index: 2245235 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3995. Min Act: -0.1700
Data Index: 1570472 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3838. Min Act: -0.1700
Data Index: 5429599 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.4151. Min Act: -0.1700
Data Index: 4777282 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3838. Min Act: -0.1700
Data Index: 6056451 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3681. Min Act: -0.1700
Data Index: 2642145 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3681. Min Act: -0.1700
Data Index: 1146966 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3838. Min Act: -0.1700
Data Index: 5763455 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3838. Min Act: -0.1700
Data Index: 877218 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3367. Min Act: -0.1700
Data Index: 41892 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3681. Min Act: -0.1700
Data Index: 5514100 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3367. Min Act: -0.1700
Data Index: 2815828 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3210. Min Act: -0.1700
Data Index: 3445992 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3053. Min Act: -0.1700
Data Index: 3598853 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3367. Min Act: -0.1700
Data Index: 6291599 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3367. Min Act: -0.1700
Data Index: 3709677 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4465. Min Range: -3.4465
Max Act: 3.3681. Min Act: -0.1700
Data Index: 7296281 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19