Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.6463. Min Act: -0.1700
Data Index: 4744572 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.4114. Min Act: -0.1700
Data Index: 985093 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.3016. Min Act: -0.1700
Data Index: 69413 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.2859. Min Act: -0.1700
Data Index: 2735433 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.2702. Min Act: -0.1700
Data Index: 6321703 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.2702. Min Act: -0.1700
Data Index: 6610663 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.2545. Min Act: -0.1700
Data Index: 5530336 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.2073. Min Act: -0.1700
Data Index: 98310 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.2073. Min Act: -0.1700
Data Index: 845978 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1601. Min Act: -0.1700
Data Index: 6622159 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1759. Min Act: -0.1700
Data Index: 3229999 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1916. Min Act: -0.1700
Data Index: 1448628 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1444. Min Act: -0.1700
Data Index: 460750 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1286. Min Act: -0.1700
Data Index: 4045723 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1444. Min Act: -0.1700
Data Index: 2406515 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1286. Min Act: -0.1700
Data Index: 3155214 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1129. Min Act: -0.1700
Data Index: 6160162 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1129. Min Act: -0.1700
Data Index: 4267969 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1129. Min Act: -0.1700
Data Index: 1205941 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6463. Min Range: -3.6463
Max Act: 3.1129. Min Act: -0.1700
Data Index: 5611407 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19