Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2760 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.7823. Min Act: -0.1700
Data Index: 5360945 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.7823. Min Act: -0.1700
Data Index: 7513817 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.7511. Min Act: -0.1700
Data Index: 6753950 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.6886. Min Act: -0.1700
Data Index: 1984531 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.6261. Min Act: -0.1700
Data Index: 3089961 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.5323. Min Act: -0.1700
Data Index: 1183065 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.4698. Min Act: -0.1700
Data Index: 2345585 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.4386. Min Act: -0.1700
Data Index: 1281032 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.4386. Min Act: -0.1700
Data Index: 3498111 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.4386. Min Act: -0.1700
Data Index: 6994225 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.4386. Min Act: -0.1700
Data Index: 4307315 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.4073. Min Act: -0.1700
Data Index: 52275 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.3448. Min Act: -0.1700
Data Index: 132459 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.3448. Min Act: -0.1700
Data Index: 7577161 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.3448. Min Act: -0.1700
Data Index: 1081524 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.3136. Min Act: -0.1700
Data Index: 3200247 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.2511. Min Act: -0.1700
Data Index: 5375136 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.2511. Min Act: -0.1700
Data Index: 2374061 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.2198. Min Act: -0.1700
Data Index: 4295616 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7823. Min Range: -6.7823
Max Act: 6.1886. Min Act: -0.1700
Data Index: 4160324 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19