Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2044 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0868. Min Range: -5.0868
Max Act: 5.0868. Min Act: -0.1700
Data Index: 1013846 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.8993. Min Act: -0.1700
Data Index: 6984676 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.8681. Min Act: -0.1700
Data Index: 3776218 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.8681. Min Act: -0.1700
Data Index: 5617155 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.8368. Min Act: -0.1700
Data Index: 2303021 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.8368. Min Act: -0.1700
Data Index: 4565941 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.8056. Min Act: -0.1700
Data Index: 4147283 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.8056. Min Act: -0.1700
Data Index: 6497526 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.7743. Min Act: -0.1700
Data Index: 7267462 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.7743. Min Act: -0.1700
Data Index: 5398740 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.7743. Min Act: -0.1700
Data Index: 8078330 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.7431. Min Act: -0.1700
Data Index: 2994684 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.7431. Min Act: -0.1700
Data Index: 4843019 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.7431. Min Act: -0.1700
Data Index: 6890547 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.7118. Min Act: -0.1700
Data Index: 3477294 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.7118. Min Act: -0.1700
Data Index: 3735970 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.6806. Min Act: -0.1700
Data Index: 2198829 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.7118. Min Act: -0.1700
Data Index: 5471080 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.7118. Min Act: -0.1700
Data Index: 1677407 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0868. Min Range: -5.0868
Max Act: 4.7118. Min Act: -0.1700
Data Index: 1838423 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19