Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3798 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.6367. Min Act: -0.1700
Data Index: 8748477 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.6367. Min Act: -0.1700
Data Index: 5936784 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.5741. Min Act: -0.1700
Data Index: 7138578 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.5584. Min Act: -0.1700
Data Index: 616483 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.5427. Min Act: -0.1700
Data Index: 8571733 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.5584. Min Act: -0.1700
Data Index: 1888453 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.4958. Min Act: -0.1700
Data Index: 5620612 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.5114. Min Act: -0.1700
Data Index: 3288640 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.5271. Min Act: -0.1700
Data Index: 2358696 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.4801. Min Act: -0.1700
Data Index: 4590157 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.4644. Min Act: -0.1700
Data Index: 5936785 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.4801. Min Act: -0.1700
Data Index: 6169482 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.4801. Min Act: -0.1700
Data Index: 5743851 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.4801. Min Act: -0.1700
Data Index: 1530798 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.4801. Min Act: -0.1700
Data Index: 5936787 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.4644. Min Act: -0.1700
Data Index: 7075054 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.4644. Min Act: -0.1700
Data Index: 3035775 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.4174. Min Act: -0.1700
Data Index: 1053868 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.4488. Min Act: -0.1700
Data Index: 288827 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6367. Min Range: -3.6367
Max Act: 3.4488. Min Act: -0.1700
Data Index: 2560125 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19