Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3603 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6027. Min Range: -7.6027
Max Act: 7.6027. Min Act: -0.1700
Data Index: 1440824 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6027. Min Range: -7.6027
Max Act: 7.3214. Min Act: -0.1700
Data Index: 7114806 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6027. Min Range: -7.6027
Max Act: 7.2277. Min Act: -0.1700
Data Index: 4378764 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6027. Min Range: -7.6027
Max Act: 7.1652. Min Act: -0.1700
Data Index: 6867843 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6027. Min Range: -7.6027
Max Act: 7.0714. Min Act: -0.1700
Data Index: 4048556 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6027. Min Range: -7.6027
Max Act: 7.0402. Min Act: -0.1700
Data Index: 2424078 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6027. Min Range: -7.6027
Max Act: 7.0402. Min Act: -0.1700
Data Index: 4434553 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6027. Min Range: -7.6027
Max Act: 6.9152. Min Act: -0.1700
Data Index: 277407 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6027. Min Range: -7.6027
Max Act: 6.8527. Min Act: -0.1700
Data Index: 867536 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6027. Min Range: -7.6027
Max Act: 6.8527. Min Act: -0.1700
Data Index: 2792490 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6027. Min Range: -7.6027
Max Act: 6.7902. Min Act: -0.1700
Data Index: 2468056 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6027. Min Range: -7.6027
Max Act: 6.7902. Min Act: -0.1700
Data Index: 6730793 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6027. Min Range: -7.6027
Max Act: 6.7902. Min Act: -0.1700
Data Index: 6885823 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6027. Min Range: -7.6027
Max Act: 6.7902. Min Act: -0.1700
Data Index: 577625 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6027. Min Range: -7.6027
Max Act: 6.7277. Min Act: -0.1700
Data Index: 5838236 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6027. Min Range: -7.6027
Max Act: 6.7589. Min Act: -0.1700
Data Index: 7954818 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6027. Min Range: -7.6027
Max Act: 6.7589. Min Act: -0.1700
Data Index: 7037149 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6027. Min Range: -7.6027
Max Act: 6.7277. Min Act: -0.1700
Data Index: 259939 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6027. Min Range: -7.6027
Max Act: 6.7277. Min Act: -0.1700
Data Index: 1750627 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6027. Min Range: -7.6027
Max Act: 6.7277. Min Act: -0.1700
Data Index: 1651553 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19