Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 350 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7078. Min Range: -8.7078
Max Act: 8.7078. Min Act: -0.1700
Data Index: 3041310 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7078. Min Range: -8.7078
Max Act: 8.5828. Min Act: -0.1700
Data Index: 6540862 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7078. Min Range: -8.7078
Max Act: 8.3328. Min Act: -0.1700
Data Index: 7312403 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7078. Min Range: -8.7078
Max Act: 8.2703. Min Act: -0.1700
Data Index: 3443608 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7078. Min Range: -8.7078
Max Act: 8.0828. Min Act: -0.1700
Data Index: 252812 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7078. Min Range: -8.7078
Max Act: 7.9578. Min Act: -0.1700
Data Index: 3864969 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7078. Min Range: -8.7078
Max Act: 7.9578. Min Act: -0.1700
Data Index: 6342920 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7078. Min Range: -8.7078
Max Act: 7.8328. Min Act: -0.1700
Data Index: 1920148 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7078. Min Range: -8.7078
Max Act: 7.7703. Min Act: -0.1700
Data Index: 8606654 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7078. Min Range: -8.7078
Max Act: 7.8328. Min Act: -0.1700
Data Index: 4109464 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7078. Min Range: -8.7078
Max Act: 7.7703. Min Act: -0.1700
Data Index: 4529171 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7078. Min Range: -8.7078
Max Act: 7.7703. Min Act: -0.1700
Data Index: 7766333 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7078. Min Range: -8.7078
Max Act: 7.7078. Min Act: -0.1700
Data Index: 6181157 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7078. Min Range: -8.7078
Max Act: 7.7078. Min Act: -0.1700
Data Index: 1888886 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7078. Min Range: -8.7078
Max Act: 7.6453. Min Act: -0.1700
Data Index: 6586473 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7078. Min Range: -8.7078
Max Act: 7.6453. Min Act: -0.1700
Data Index: 1377788 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7078. Min Range: -8.7078
Max Act: 7.6453. Min Act: -0.1700
Data Index: 5174099 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7078. Min Range: -8.7078
Max Act: 7.5828. Min Act: -0.1700
Data Index: 1021046 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7078. Min Range: -8.7078
Max Act: 7.5828. Min Act: -0.1700
Data Index: 3184356 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7078. Min Range: -8.7078
Max Act: 7.5828. Min Act: -0.1700
Data Index: 5592425 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19