Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3596 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4918. Min Range: -4.4918
Max Act: 4.4918. Min Act: -0.1700
Data Index: 3060022 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4918. Min Range: -4.4918
Max Act: 4.3043. Min Act: -0.1700
Data Index: 1011345 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4918. Min Range: -4.4918
Max Act: 4.1792. Min Act: -0.1700
Data Index: 1610202 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4918. Min Range: -4.4918
Max Act: 4.2105. Min Act: -0.1700
Data Index: 1224717 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4918. Min Range: -4.4918
Max Act: 4.1480. Min Act: -0.1700
Data Index: 3204269 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4918. Min Range: -4.4918
Max Act: 4.1792. Min Act: -0.1700
Data Index: 6291096 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4918. Min Range: -4.4918
Max Act: 4.1480. Min Act: -0.1700
Data Index: 8216970 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4918. Min Range: -4.4918
Max Act: 4.1480. Min Act: -0.1700
Data Index: 4359576 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4918. Min Range: -4.4918
Max Act: 4.0855. Min Act: -0.1700
Data Index: 6787134 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4918. Min Range: -4.4918
Max Act: 4.1167. Min Act: -0.1700
Data Index: 1659119 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4918. Min Range: -4.4918
Max Act: 4.1167. Min Act: -0.1700
Data Index: 8423743 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4918. Min Range: -4.4918
Max Act: 4.1167. Min Act: -0.1700
Data Index: 1835970 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4918. Min Range: -4.4918
Max Act: 3.9917. Min Act: -0.1700
Data Index: 232688 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4918. Min Range: -4.4918
Max Act: 4.0542. Min Act: -0.1700
Data Index: 2433843 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4918. Min Range: -4.4918
Max Act: 4.0542. Min Act: -0.1700
Data Index: 4155141 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4918. Min Range: -4.4918
Max Act: 4.0542. Min Act: -0.1700
Data Index: 2919743 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4918. Min Range: -4.4918
Max Act: 4.0542. Min Act: -0.1700
Data Index: 4943710 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4918. Min Range: -4.4918
Max Act: 4.0230. Min Act: -0.1700
Data Index: 7038254 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4918. Min Range: -4.4918
Max Act: 4.0230. Min Act: -0.1700
Data Index: 337878 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4918. Min Range: -4.4918
Max Act: 3.9917. Min Act: -0.1700
Data Index: 3867938 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19