Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4395 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.6502. Min Act: -0.1700
Data Index: 8386848 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.6342. Min Act: -0.1700
Data Index: 4595427 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.6181. Min Act: -0.1700
Data Index: 2577519 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.6181. Min Act: -0.1700
Data Index: 5762278 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.5698. Min Act: -0.1700
Data Index: 1667736 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.5698. Min Act: -0.1700
Data Index: 1373484 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.5859. Min Act: -0.1700
Data Index: 5027037 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.5698. Min Act: -0.1700
Data Index: 7024330 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.5537. Min Act: -0.1700
Data Index: 7842032 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.5537. Min Act: -0.1700
Data Index: 5266395 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.5537. Min Act: -0.1700
Data Index: 5704262 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.5537. Min Act: -0.1700
Data Index: 5266398 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.5375. Min Act: -0.1700
Data Index: 6142131 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.5375. Min Act: -0.1700
Data Index: 6426096 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.5052. Min Act: -0.1700
Data Index: 5225341 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.5214. Min Act: -0.1700
Data Index: 821037 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.5375. Min Act: -0.1700
Data Index: 5728745 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.5375. Min Act: -0.1700
Data Index: 6383159 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.5214. Min Act: -0.1700
Data Index: 7597631 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6502. Min Range: -2.6502
Max Act: 2.5214. Min Act: -0.1700
Data Index: 5604861 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19