Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4878 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.6324. Min Act: -0.1700
Data Index: 37984 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.3512. Min Act: -0.1700
Data Index: 838180 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.2574. Min Act: -0.1700
Data Index: 3484223 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.1949. Min Act: -0.1700
Data Index: 1576469 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.1324. Min Act: -0.1700
Data Index: 2906224 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.0699. Min Act: -0.1700
Data Index: 7823289 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.0699. Min Act: -0.1700
Data Index: 4823663 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.0074. Min Act: -0.1700
Data Index: 1014380 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6324. Min Range: -6.6324
Max Act: 5.9762. Min Act: -0.1700
Data Index: 6722468 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6324. Min Range: -6.6324
Max Act: 5.9449. Min Act: -0.1700
Data Index: 5516709 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6324. Min Range: -6.6324
Max Act: 5.9449. Min Act: -0.1700
Data Index: 7738326 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6324. Min Range: -6.6324
Max Act: 5.9449. Min Act: -0.1700
Data Index: 42662 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6324. Min Range: -6.6324
Max Act: 5.9137. Min Act: -0.1700
Data Index: 4124973 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6324. Min Range: -6.6324
Max Act: 5.8824. Min Act: -0.1700
Data Index: 1855024 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6324. Min Range: -6.6324
Max Act: 5.8824. Min Act: -0.1700
Data Index: 1990048 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6324. Min Range: -6.6324
Max Act: 5.8512. Min Act: -0.1700
Data Index: 6452702 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6324. Min Range: -6.6324
Max Act: 5.8512. Min Act: -0.1700
Data Index: 4309692 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6324. Min Range: -6.6324
Max Act: 5.8512. Min Act: -0.1700
Data Index: 2663944 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6324. Min Range: -6.6324
Max Act: 5.8199. Min Act: -0.1700
Data Index: 4677626 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6324. Min Range: -6.6324
Max Act: 5.8512. Min Act: -0.1700
Data Index: 2272465 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19