Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5958 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2159. Min Range: -6.2159
Max Act: 6.2159. Min Act: -0.1700
Data Index: 5450466 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2159. Min Range: -6.2159
Max Act: 6.0596. Min Act: -0.1700
Data Index: 4044140 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2159. Min Range: -6.2159
Max Act: 6.0284. Min Act: -0.1700
Data Index: 3309247 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2159. Min Range: -6.2159
Max Act: 5.9971. Min Act: -0.1700
Data Index: 6171824 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2159. Min Range: -6.2159
Max Act: 5.9659. Min Act: -0.1700
Data Index: 5533524 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2159. Min Range: -6.2159
Max Act: 5.9346. Min Act: -0.1700
Data Index: 7304556 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2159. Min Range: -6.2159
Max Act: 5.9034. Min Act: -0.1700
Data Index: 6392716 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2159. Min Range: -6.2159
Max Act: 5.9034. Min Act: -0.1700
Data Index: 6171818 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2159. Min Range: -6.2159
Max Act: 5.9034. Min Act: -0.1700
Data Index: 387029 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2159. Min Range: -6.2159
Max Act: 5.8721. Min Act: -0.1700
Data Index: 8798075 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2159. Min Range: -6.2159
Max Act: 5.8721. Min Act: -0.1700
Data Index: 6626395 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2159. Min Range: -6.2159
Max Act: 5.8409. Min Act: -0.1700
Data Index: 7768648 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2159. Min Range: -6.2159
Max Act: 5.8409. Min Act: -0.1700
Data Index: 5321229 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2159. Min Range: -6.2159
Max Act: 5.8096. Min Act: -0.1700
Data Index: 5249916 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2159. Min Range: -6.2159
Max Act: 5.8409. Min Act: -0.1700
Data Index: 3734459 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2159. Min Range: -6.2159
Max Act: 5.8096. Min Act: -0.1700
Data Index: 7353152 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2159. Min Range: -6.2159
Max Act: 5.8409. Min Act: -0.1700
Data Index: 3379897 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2159. Min Range: -6.2159
Max Act: 5.8096. Min Act: -0.1700
Data Index: 5198113 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2159. Min Range: -6.2159
Max Act: 5.8096. Min Act: -0.1700
Data Index: 2714327 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2159. Min Range: -6.2159
Max Act: 5.7784. Min Act: -0.1700
Data Index: 171810 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19