Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6202 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0391. Min Range: -7.0391
Max Act: 7.0391. Min Act: -0.1700
Data Index: 6944929 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0391. Min Range: -7.0391
Max Act: 6.9454. Min Act: -0.1700
Data Index: 6989724 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0391. Min Range: -7.0391
Max Act: 6.9141. Min Act: -0.1700
Data Index: 7351125 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0391. Min Range: -7.0391
Max Act: 6.8829. Min Act: -0.1700
Data Index: 4365711 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0391. Min Range: -7.0391
Max Act: 6.8516. Min Act: -0.1700
Data Index: 6191292 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0391. Min Range: -7.0391
Max Act: 6.8204. Min Act: -0.1700
Data Index: 2952581 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0391. Min Range: -7.0391
Max Act: 6.7891. Min Act: -0.1700
Data Index: 7810502 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0391. Min Range: -7.0391
Max Act: 6.7891. Min Act: -0.1700
Data Index: 4163652 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0391. Min Range: -7.0391
Max Act: 6.7579. Min Act: -0.1700
Data Index: 742201 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0391. Min Range: -7.0391
Max Act: 6.7579. Min Act: -0.1700
Data Index: 8600901 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0391. Min Range: -7.0391
Max Act: 6.7579. Min Act: -0.1700
Data Index: 7709623 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0391. Min Range: -7.0391
Max Act: 6.7579. Min Act: -0.1700
Data Index: 2993819 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0391. Min Range: -7.0391
Max Act: 6.7266. Min Act: -0.1700
Data Index: 6863402 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0391. Min Range: -7.0391
Max Act: 6.6954. Min Act: -0.1700
Data Index: 5860302 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0391. Min Range: -7.0391
Max Act: 6.7266. Min Act: -0.1700
Data Index: 3270712 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0391. Min Range: -7.0391
Max Act: 6.7266. Min Act: -0.1700
Data Index: 7378762 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0391. Min Range: -7.0391
Max Act: 6.7579. Min Act: -0.1700
Data Index: 7599213 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0391. Min Range: -7.0391
Max Act: 6.6954. Min Act: -0.1700
Data Index: 7331001 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0391. Min Range: -7.0391
Max Act: 6.7266. Min Act: -0.1700
Data Index: 2990430 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0391. Min Range: -7.0391
Max Act: 6.6954. Min Act: -0.1700
Data Index: 1565047 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19