Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5857 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3993. Min Range: -6.3993
Max Act: 6.3993. Min Act: -0.1700
Data Index: 2117315 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3993. Min Range: -6.3993
Max Act: 5.9306. Min Act: -0.1700
Data Index: 6903723 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3993. Min Range: -6.3993
Max Act: 5.8681. Min Act: -0.1700
Data Index: 890965 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3993. Min Range: -6.3993
Max Act: 5.8368. Min Act: -0.1700
Data Index: 6059236 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3993. Min Range: -6.3993
Max Act: 5.8368. Min Act: -0.1700
Data Index: 5943929 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3993. Min Range: -6.3993
Max Act: 5.8056. Min Act: -0.1700
Data Index: 4948374 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3993. Min Range: -6.3993
Max Act: 5.8056. Min Act: -0.1700
Data Index: 6073089 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3993. Min Range: -6.3993
Max Act: 5.8056. Min Act: -0.1700
Data Index: 7997707 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3993. Min Range: -6.3993
Max Act: 5.7743. Min Act: -0.1700
Data Index: 8442390 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3993. Min Range: -6.3993
Max Act: 5.7743. Min Act: -0.1700
Data Index: 3486754 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3993. Min Range: -6.3993
Max Act: 5.7431. Min Act: -0.1700
Data Index: 608742 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3993. Min Range: -6.3993
Max Act: 5.7431. Min Act: -0.1700
Data Index: 1086263 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3993. Min Range: -6.3993
Max Act: 5.7431. Min Act: -0.1700
Data Index: 2522742 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3993. Min Range: -6.3993
Max Act: 5.7431. Min Act: -0.1700
Data Index: 3880122 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3993. Min Range: -6.3993
Max Act: 5.7118. Min Act: -0.1700
Data Index: 5366715 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3993. Min Range: -6.3993
Max Act: 5.6806. Min Act: -0.1700
Data Index: 3824428 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3993. Min Range: -6.3993
Max Act: 5.7118. Min Act: -0.1700
Data Index: 3052574 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3993. Min Range: -6.3993
Max Act: 5.7118. Min Act: -0.1700
Data Index: 6947783 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3993. Min Range: -6.3993
Max Act: 5.6806. Min Act: -0.1700
Data Index: 3670900 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3993. Min Range: -6.3993
Max Act: 5.7118. Min Act: -0.1700
Data Index: 2024037 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19