Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3540 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.6085. Min Act: -0.1700
Data Index: 5005207 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.5773. Min Act: -0.1700
Data Index: 8763676 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.5148. Min Act: -0.1700
Data Index: 541212 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.4835. Min Act: -0.1700
Data Index: 7319741 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.4835. Min Act: -0.1700
Data Index: 3314995 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.4835. Min Act: -0.1700
Data Index: 3978489 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.4835. Min Act: -0.1700
Data Index: 5340886 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.4523. Min Act: -0.1700
Data Index: 5488013 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.4523. Min Act: -0.1700
Data Index: 5730003 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.4523. Min Act: -0.1700
Data Index: 841223 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.4210. Min Act: -0.1700
Data Index: 7148487 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.3585. Min Act: -0.1700
Data Index: 7036664 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.3585. Min Act: -0.1700
Data Index: 1401924 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.3273. Min Act: -0.1700
Data Index: 3122380 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.2960. Min Act: -0.1700
Data Index: 4517401 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.2960. Min Act: -0.1700
Data Index: 1441385 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.2960. Min Act: -0.1700
Data Index: 8018972 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.2960. Min Act: -0.1700
Data Index: 6818342 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.2960. Min Act: -0.1700
Data Index: 6714287 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6085. Min Range: -4.6085
Max Act: 4.2960. Min Act: -0.1700
Data Index: 859025 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19