Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3038 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.8868. Min Act: -0.1700
Data Index: 4129826 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.8868. Min Act: -0.1700
Data Index: 6487640 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.8868. Min Act: -0.1700
Data Index: 8582602 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.8556. Min Act: -0.1700
Data Index: 4807591 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.8243. Min Act: -0.1700
Data Index: 7921165 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.7306. Min Act: -0.1700
Data Index: 4151634 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.6681. Min Act: -0.1700
Data Index: 5639079 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.6681. Min Act: -0.1700
Data Index: 4710770 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.6368. Min Act: -0.1700
Data Index: 740275 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.6681. Min Act: -0.1700
Data Index: 2514275 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.6681. Min Act: -0.1700
Data Index: 107727 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.6368. Min Act: -0.1700
Data Index: 2775410 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.6056. Min Act: -0.1700
Data Index: 3806249 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.6056. Min Act: -0.1700
Data Index: 5908951 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.6056. Min Act: -0.1700
Data Index: 4857078 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.5743. Min Act: -0.1700
Data Index: 584021 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.5743. Min Act: -0.1700
Data Index: 1013308 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.5743. Min Act: -0.1700
Data Index: 5908949 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.5431. Min Act: -0.1700
Data Index: 2517643 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8868. Min Range: -4.8868
Max Act: 4.5431. Min Act: -0.1700
Data Index: 5908950 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19