Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.6030. Min Act: -0.1700
Data Index: 8830001 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.5717. Min Act: -0.1700
Data Index: 6838024 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.4780. Min Act: -0.1700
Data Index: 3767014 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.4155. Min Act: -0.1700
Data Index: 6264397 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.4155. Min Act: -0.1700
Data Index: 2876874 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.3842. Min Act: -0.1700
Data Index: 6264399 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.3530. Min Act: -0.1700
Data Index: 7359845 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.3530. Min Act: -0.1700
Data Index: 6108642 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.2592. Min Act: -0.1700
Data Index: 1292638 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.2592. Min Act: -0.1700
Data Index: 5324371 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.2592. Min Act: -0.1700
Data Index: 1912425 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.2280. Min Act: -0.1700
Data Index: 6703996 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.2280. Min Act: -0.1700
Data Index: 7341396 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.1967. Min Act: -0.1700
Data Index: 5847371 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.1655. Min Act: -0.1700
Data Index: 5943635 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.1655. Min Act: -0.1700
Data Index: 1706792 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.1655. Min Act: -0.1700
Data Index: 790593 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.1342. Min Act: -0.1700
Data Index: 312009 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.1030. Min Act: -0.1700
Data Index: 6264400 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6030. Min Range: -6.6030
Max Act: 6.1342. Min Act: -0.1700
Data Index: 5604161 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19