Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1935 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.8166. Min Act: -0.1700
Data Index: 3867466 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.7229. Min Act: -0.1700
Data Index: 4364412 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.6916. Min Act: -0.1700
Data Index: 4635873 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.7541. Min Act: -0.1700
Data Index: 7865510 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.6916. Min Act: -0.1700
Data Index: 4075044 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.6604. Min Act: -0.1700
Data Index: 2018946 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.6916. Min Act: -0.1700
Data Index: 5953216 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.6604. Min Act: -0.1700
Data Index: 7008423 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.6604. Min Act: -0.1700
Data Index: 3415235 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.6604. Min Act: -0.1700
Data Index: 1884136 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.6604. Min Act: -0.1700
Data Index: 2701847 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.6604. Min Act: -0.1700
Data Index: 4528801 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.6291. Min Act: -0.1700
Data Index: 5212887 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.6291. Min Act: -0.1700
Data Index: 6912433 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.6291. Min Act: -0.1700
Data Index: 2541324 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.6291. Min Act: -0.1700
Data Index: 8785385 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.6291. Min Act: -0.1700
Data Index: 1276692 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.5979. Min Act: -0.1700
Data Index: 3481778 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.6291. Min Act: -0.1699
Data Index: 697829 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8166. Min Range: -5.8166
Max Act: 5.6291. Min Act: -0.1700
Data Index: 5155857 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19