Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4193 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3001. Min Range: -6.3001
Max Act: 6.3001. Min Act: -0.1700
Data Index: 5703974 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3001. Min Range: -6.3001
Max Act: 6.2063. Min Act: -0.1700
Data Index: 4849828 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3001. Min Range: -6.3001
Max Act: 6.1751. Min Act: -0.1700
Data Index: 6397542 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3001. Min Range: -6.3001
Max Act: 6.1126. Min Act: -0.1700
Data Index: 926238 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3001. Min Range: -6.3001
Max Act: 6.0501. Min Act: -0.1700
Data Index: 1198780 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3001. Min Range: -6.3001
Max Act: 6.0188. Min Act: -0.1700
Data Index: 5805412 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3001. Min Range: -6.3001
Max Act: 6.0188. Min Act: -0.1700
Data Index: 7798416 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3001. Min Range: -6.3001
Max Act: 6.0188. Min Act: -0.1700
Data Index: 8146873 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3001. Min Range: -6.3001
Max Act: 5.9876. Min Act: -0.1700
Data Index: 1682073 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3001. Min Range: -6.3001
Max Act: 5.9563. Min Act: -0.1700
Data Index: 4807019 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3001. Min Range: -6.3001
Max Act: 5.9563. Min Act: -0.1700
Data Index: 5676613 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3001. Min Range: -6.3001
Max Act: 5.9251. Min Act: -0.1700
Data Index: 7160129 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3001. Min Range: -6.3001
Max Act: 5.9251. Min Act: -0.1700
Data Index: 1976350 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3001. Min Range: -6.3001
Max Act: 5.9251. Min Act: -0.1700
Data Index: 3669738 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3001. Min Range: -6.3001
Max Act: 5.9251. Min Act: -0.1700
Data Index: 3948032 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3001. Min Range: -6.3001
Max Act: 5.9563. Min Act: -0.1700
Data Index: 4050270 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3001. Min Range: -6.3001
Max Act: 5.8626. Min Act: -0.1700
Data Index: 6243173 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3001. Min Range: -6.3001
Max Act: 5.8938. Min Act: -0.1700
Data Index: 3268211 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3001. Min Range: -6.3001
Max Act: 5.8938. Min Act: -0.1700
Data Index: 8175016 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3001. Min Range: -6.3001
Max Act: 5.8626. Min Act: -0.1700
Data Index: 1828330 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19