Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4458 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.7529. Min Act: -0.1700
Data Index: 4497968 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.8154. Min Act: -0.1700
Data Index: 4045266 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.5654. Min Act: -0.1700
Data Index: 8081339 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.5029. Min Act: -0.1700
Data Index: 368927 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.5029. Min Act: -0.1700
Data Index: 5436134 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.5029. Min Act: -0.1700
Data Index: 5121595 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.5029. Min Act: -0.1700
Data Index: 5526508 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.5029. Min Act: -0.1700
Data Index: 5676602 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.4404. Min Act: -0.1700
Data Index: 7547593 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.3779. Min Act: -0.1700
Data Index: 7676878 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.3779. Min Act: -0.1700
Data Index: 5024070 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.3779. Min Act: -0.1700
Data Index: 2506630 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.3154. Min Act: -0.1700
Data Index: 3966114 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.3779. Min Act: -0.1700
Data Index: 4562136 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.3779. Min Act: -0.1700
Data Index: 2980171 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.3779. Min Act: -0.1700
Data Index: 2750136 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.3154. Min Act: -0.1700
Data Index: 4451262 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.2529. Min Act: -0.1700
Data Index: 1018004 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.3154. Min Act: -0.1700
Data Index: 259837 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8154. Min Range: -8.8154
Max Act: 8.3154. Min Act: -0.1700
Data Index: 1124322 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19