Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2745 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.3609. Min Act: -0.1700
Data Index: 1270674 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.2623. Min Act: -0.1700
Data Index: 7803677 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.1795. Min Act: -0.1700
Data Index: 7785796 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.1795. Min Act: -0.1700
Data Index: 5108042 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.1795. Min Act: -0.1700
Data Index: 3374398 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.1628. Min Act: -0.1700
Data Index: 232588 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.1628. Min Act: -0.1700
Data Index: 4077689 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.1628. Min Act: -0.1700
Data Index: 7750956 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.1462. Min Act: -0.1700
Data Index: 2833338 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.1462. Min Act: -0.1700
Data Index: 5445433 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.1462. Min Act: -0.1700
Data Index: 4135317 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.1295. Min Act: -0.1700
Data Index: 8161119 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.1462. Min Act: -0.1700
Data Index: 8588147 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.1462. Min Act: -0.1700
Data Index: 6030597 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.1462. Min Act: -0.1700
Data Index: 5137515 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.1295. Min Act: -0.1700
Data Index: 8394450 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.1295. Min Act: -0.1700
Data Index: 7092332 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.0960. Min Act: -0.1700
Data Index: 6858527 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.1128. Min Act: -0.1700
Data Index: 698806 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3609. Min Range: -2.3609
Max Act: 2.1128. Min Act: -0.1700
Data Index: 2764127 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19