Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8125. Min Range: -5.8125
Max Act: 5.8125. Min Act: -0.1700
Data Index: 4434663 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8125. Min Range: -5.8125
Max Act: 5.1875. Min Act: -0.1700
Data Index: 572707 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8125. Min Range: -5.8125
Max Act: 5.1562. Min Act: -0.1700
Data Index: 3820443 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8125. Min Range: -5.8125
Max Act: 5.1562. Min Act: -0.1700
Data Index: 3807864 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8125. Min Range: -5.8125
Max Act: 5.0937. Min Act: -0.1700
Data Index: 3987857 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8125. Min Range: -5.8125
Max Act: 5.0625. Min Act: -0.1700
Data Index: 2898305 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8125. Min Range: -5.8125
Max Act: 5.0625. Min Act: -0.1700
Data Index: 6632162 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8125. Min Range: -5.8125
Max Act: 5.0312. Min Act: -0.1700
Data Index: 8674389 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8125. Min Range: -5.8125
Max Act: 5.0312. Min Act: -0.1700
Data Index: 908606 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8125. Min Range: -5.8125
Max Act: 5.0312. Min Act: -0.1700
Data Index: 5496653 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8125. Min Range: -5.8125
Max Act: 5.0312. Min Act: -0.1700
Data Index: 96474 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8125. Min Range: -5.8125
Max Act: 5.0000. Min Act: -0.1700
Data Index: 250646 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8125. Min Range: -5.8125
Max Act: 5.0312. Min Act: -0.1700
Data Index: 8586073 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8125. Min Range: -5.8125
Max Act: 5.0000. Min Act: -0.1700
Data Index: 6588323 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8125. Min Range: -5.8125
Max Act: 5.0000. Min Act: -0.1700
Data Index: 3267558 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8125. Min Range: -5.8125
Max Act: 4.9375. Min Act: -0.1700
Data Index: 5180080 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8125. Min Range: -5.8125
Max Act: 4.9375. Min Act: -0.1700
Data Index: 5620712 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8125. Min Range: -5.8125
Max Act: 4.9375. Min Act: -0.1700
Data Index: 6775268 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8125. Min Range: -5.8125
Max Act: 4.9687. Min Act: -0.1700
Data Index: 4114482 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8125. Min Range: -5.8125
Max Act: 4.9375. Min Act: -0.1700
Data Index: 7661760 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19