Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2825 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.6403. Min Act: -0.1700
Data Index: 2570013 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.5153. Min Act: -0.1700
Data Index: 4103626 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.4528. Min Act: -0.1700
Data Index: 2393406 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.4840. Min Act: -0.1700
Data Index: 263785 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.4840. Min Act: -0.1700
Data Index: 2474883 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.3590. Min Act: -0.1700
Data Index: 7487984 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.2965. Min Act: -0.1700
Data Index: 5550367 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.2340. Min Act: -0.1700
Data Index: 2691223 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.2653. Min Act: -0.1700
Data Index: 8076395 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.2340. Min Act: -0.1700
Data Index: 866704 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.1090. Min Act: -0.1700
Data Index: 1536650 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.1403. Min Act: -0.1700
Data Index: 6638834 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.1403. Min Act: -0.1700
Data Index: 6717762 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.1403. Min Act: -0.1700
Data Index: 4983052 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.1090. Min Act: -0.1700
Data Index: 586241 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.0778. Min Act: -0.1700
Data Index: 7548151 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.0465. Min Act: -0.1700
Data Index: 8275692 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.0465. Min Act: -0.1700
Data Index: 5592318 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.0465. Min Act: -0.1700
Data Index: 4448331 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6403. Min Range: -5.6403
Max Act: 5.0153. Min Act: -0.1700
Data Index: 881460 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19