Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4520 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2166. Min Range: -8.2166
Max Act: 8.2166. Min Act: -0.1700
Data Index: 5446913 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2166. Min Range: -8.2166
Max Act: 8.0916. Min Act: -0.1700
Data Index: 4062069 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2166. Min Range: -8.2166
Max Act: 7.9041. Min Act: -0.1700
Data Index: 164537 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2166. Min Range: -8.2166
Max Act: 7.7791. Min Act: -0.1700
Data Index: 8148291 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2166. Min Range: -8.2166
Max Act: 7.7791. Min Act: -0.1700
Data Index: 806087 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2166. Min Range: -8.2166
Max Act: 7.7479. Min Act: -0.1700
Data Index: 5882789 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2166. Min Range: -8.2166
Max Act: 7.7166. Min Act: -0.1700
Data Index: 3521810 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2166. Min Range: -8.2166
Max Act: 7.7166. Min Act: -0.1700
Data Index: 2681758 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2166. Min Range: -8.2166
Max Act: 7.7166. Min Act: -0.1700
Data Index: 7601797 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2166. Min Range: -8.2166
Max Act: 7.6854. Min Act: -0.1700
Data Index: 91474 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2166. Min Range: -8.2166
Max Act: 7.6541. Min Act: -0.1700
Data Index: 4719662 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2166. Min Range: -8.2166
Max Act: 7.6229. Min Act: -0.1700
Data Index: 1163181 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2166. Min Range: -8.2166
Max Act: 7.6541. Min Act: -0.1700
Data Index: 1589310 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2166. Min Range: -8.2166
Max Act: 7.6229. Min Act: -0.1700
Data Index: 3489508 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2166. Min Range: -8.2166
Max Act: 7.6229. Min Act: -0.1700
Data Index: 7507626 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2166. Min Range: -8.2166
Max Act: 7.5604. Min Act: -0.1700
Data Index: 7069477 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2166. Min Range: -8.2166
Max Act: 7.5604. Min Act: -0.1700
Data Index: 7353943 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2166. Min Range: -8.2166
Max Act: 7.5291. Min Act: -0.1700
Data Index: 3593197 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2166. Min Range: -8.2166
Max Act: 7.5291. Min Act: -0.1700
Data Index: 4479028 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2166. Min Range: -8.2166
Max Act: 7.4979. Min Act: -0.1700
Data Index: 6322710 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19