Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2699 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8646. Min Range: -7.8646
Max Act: 7.8646. Min Act: -0.1700
Data Index: 7903161 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8646. Min Range: -7.8646
Max Act: 7.3021. Min Act: -0.1700
Data Index: 457512 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8646. Min Range: -7.8646
Max Act: 7.2708. Min Act: -0.1700
Data Index: 1642230 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8646. Min Range: -7.8646
Max Act: 7.1458. Min Act: -0.1700
Data Index: 5974002 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8646. Min Range: -7.8646
Max Act: 7.1458. Min Act: -0.1700
Data Index: 6877893 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8646. Min Range: -7.8646
Max Act: 7.1458. Min Act: -0.1700
Data Index: 1525847 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8646. Min Range: -7.8646
Max Act: 6.9896. Min Act: -0.1700
Data Index: 1346567 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8646. Min Range: -7.8646
Max Act: 6.9896. Min Act: -0.1700
Data Index: 6967691 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8646. Min Range: -7.8646
Max Act: 6.9896. Min Act: -0.1700
Data Index: 6344134 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8646. Min Range: -7.8646
Max Act: 6.8958. Min Act: -0.1700
Data Index: 2565511 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8646. Min Range: -7.8646
Max Act: 6.9271. Min Act: -0.1700
Data Index: 5773602 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8646. Min Range: -7.8646
Max Act: 6.8646. Min Act: -0.1700
Data Index: 6263196 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8646. Min Range: -7.8646
Max Act: 6.8646. Min Act: -0.1700
Data Index: 642120 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8646. Min Range: -7.8646
Max Act: 6.8333. Min Act: -0.1700
Data Index: 5656386 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8646. Min Range: -7.8646
Max Act: 6.8333. Min Act: -0.1700
Data Index: 3069536 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8646. Min Range: -7.8646
Max Act: 6.8646. Min Act: -0.1700
Data Index: 4057680 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8646. Min Range: -7.8646
Max Act: 6.8333. Min Act: -0.1700
Data Index: 8210804 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8646. Min Range: -7.8646
Max Act: 6.8021. Min Act: -0.1700
Data Index: 4447999 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8646. Min Range: -7.8646
Max Act: 6.8021. Min Act: -0.1700
Data Index: 4910213 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8646. Min Range: -7.8646
Max Act: 6.8021. Min Act: -0.1700
Data Index: 7619001 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19