Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3260 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.8958. Min Act: -0.1700
Data Index: 2938190 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.5833. Min Act: -0.1700
Data Index: 1257775 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.5833. Min Act: -0.1700
Data Index: 3936709 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.5833. Min Act: -0.1700
Data Index: 3629819 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.5833. Min Act: -0.1700
Data Index: 7901725 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.3958. Min Act: -0.1700
Data Index: 4203812 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.3333. Min Act: -0.1700
Data Index: 3055606 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.2708. Min Act: -0.1700
Data Index: 2901580 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.2708. Min Act: -0.1700
Data Index: 4124047 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.2708. Min Act: -0.1700
Data Index: 1300578 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.2708. Min Act: -0.1700
Data Index: 2717785 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.2083. Min Act: -0.1700
Data Index: 4008212 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.2083. Min Act: -0.1700
Data Index: 4888563 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.1458. Min Act: -0.1700
Data Index: 7079672 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.1458. Min Act: -0.1700
Data Index: 3444680 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.1458. Min Act: -0.1700
Data Index: 2641633 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.0833. Min Act: -0.1700
Data Index: 5049933 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.0833. Min Act: -0.1700
Data Index: 483066 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.0208. Min Act: -0.1700
Data Index: 4675219 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8958. Min Range: -10.8958
Max Act: 10.0208. Min Act: -0.1700
Data Index: 6077577 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19