Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4726 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1199. Min Range: -4.1199
Max Act: 4.1199. Min Act: -0.1700
Data Index: 5446083 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1199. Min Range: -4.1199
Max Act: 3.9949. Min Act: -0.1700
Data Index: 3549594 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1199. Min Range: -4.1199
Max Act: 3.9949. Min Act: -0.1700
Data Index: 4386425 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1199. Min Range: -4.1199
Max Act: 3.9636. Min Act: -0.1700
Data Index: 2016900 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1199. Min Range: -4.1199
Max Act: 3.9324. Min Act: -0.1700
Data Index: 8094551 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1199. Min Range: -4.1199
Max Act: 3.8698. Min Act: -0.1700
Data Index: 3176747 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1199. Min Range: -4.1199
Max Act: 3.8698. Min Act: -0.1700
Data Index: 3341794 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1199. Min Range: -4.1199
Max Act: 3.8542. Min Act: -0.1700
Data Index: 5535611 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1199. Min Range: -4.1199
Max Act: 3.8386. Min Act: -0.1700
Data Index: 3014667 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1199. Min Range: -4.1199
Max Act: 3.8386. Min Act: -0.1700
Data Index: 3451729 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1199. Min Range: -4.1199
Max Act: 3.8229. Min Act: -0.1700
Data Index: 1369593 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1199. Min Range: -4.1199
Max Act: 3.8229. Min Act: -0.1700
Data Index: 3176748 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1199. Min Range: -4.1199
Max Act: 3.7760. Min Act: -0.1700
Data Index: 5211230 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1199. Min Range: -4.1199
Max Act: 3.7760. Min Act: -0.1700
Data Index: 1451075 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1199. Min Range: -4.1199
Max Act: 3.7760. Min Act: -0.1700
Data Index: 905443 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1199. Min Range: -4.1199
Max Act: 3.7291. Min Act: -0.1700
Data Index: 5255938 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1199. Min Range: -4.1199
Max Act: 3.7135. Min Act: -0.1700
Data Index: 1918255 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1199. Min Range: -4.1199
Max Act: 3.7291. Min Act: -0.1700
Data Index: 6524888 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1199. Min Range: -4.1199
Max Act: 3.7291. Min Act: -0.1700
Data Index: 2583671 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1199. Min Range: -4.1199
Max Act: 3.6978. Min Act: -0.1700
Data Index: 855772 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19