Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3541 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.4194. Min Act: -0.1700
Data Index: 3625772 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.3569. Min Act: -0.1700
Data Index: 5871832 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.3569. Min Act: -0.1700
Data Index: 8488148 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.2632. Min Act: -0.1700
Data Index: 4747165 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.2319. Min Act: -0.1700
Data Index: 8456050 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.2319. Min Act: -0.1700
Data Index: 3080399 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.1694. Min Act: -0.1700
Data Index: 815934 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.1694. Min Act: -0.1700
Data Index: 355307 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.1694. Min Act: -0.1700
Data Index: 1647196 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.1694. Min Act: -0.1700
Data Index: 7990930 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.1382. Min Act: -0.1700
Data Index: 387107 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.1694. Min Act: -0.1700
Data Index: 2350736 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.0757. Min Act: -0.1700
Data Index: 67879 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.1069. Min Act: -0.1700
Data Index: 4299611 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.1069. Min Act: -0.1700
Data Index: 5746805 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.1069. Min Act: -0.1700
Data Index: 3009834 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.1069. Min Act: -0.1700
Data Index: 4662637 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.0757. Min Act: -0.1700
Data Index: 7453714 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.1069. Min Act: -0.1700
Data Index: 3835478 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4194. Min Range: -5.4194
Max Act: 5.0757. Min Act: -0.1700
Data Index: 783749 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19