Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 366 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.4593. Min Act: -0.1700
Data Index: 237129 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3966. Min Act: -0.1700
Data Index: 17493 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3966. Min Act: -0.1700
Data Index: 5692396 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.4280. Min Act: -0.1700
Data Index: 338492 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3966. Min Act: -0.1700
Data Index: 1007513 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3652. Min Act: -0.1700
Data Index: 143552 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3966. Min Act: -0.1700
Data Index: 1035188 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3652. Min Act: -0.1700
Data Index: 5474295 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3496. Min Act: -0.1700
Data Index: 6563122 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3496. Min Act: -0.1700
Data Index: 1140593 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3496. Min Act: -0.1700
Data Index: 273021 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3339. Min Act: -0.1700
Data Index: 7307303 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3496. Min Act: -0.1700
Data Index: 2826937 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3339. Min Act: -0.1700
Data Index: 149617 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3182. Min Act: -0.1700
Data Index: 1864944 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3652. Min Act: -0.1700
Data Index: 1637414 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3339. Min Act: -0.1700
Data Index: 4239437 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3182. Min Act: -0.1700
Data Index: 5905696 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3025. Min Act: -0.1700
Data Index: 5912216 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4593. Min Range: -3.4593
Max Act: 3.3025. Min Act: -0.1700
Data Index: 2242980 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19