Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 444 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0256. Min Range: -5.0256
Max Act: 5.0256. Min Act: -0.1700
Data Index: 3049984 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0256. Min Range: -5.0256
Max Act: 4.6193. Min Act: -0.1700
Data Index: 6752014 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0256. Min Range: -5.0256
Max Act: 4.5881. Min Act: -0.1700
Data Index: 3586365 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0256. Min Range: -5.0256
Max Act: 4.5881. Min Act: -0.1700
Data Index: 3695747 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0256. Min Range: -5.0256
Max Act: 4.5568. Min Act: -0.1700
Data Index: 8681876 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0256. Min Range: -5.0256
Max Act: 4.4943. Min Act: -0.1700
Data Index: 6063141 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0256. Min Range: -5.0256
Max Act: 4.4943. Min Act: -0.1700
Data Index: 6872592 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0256. Min Range: -5.0256
Max Act: 4.4631. Min Act: -0.1700
Data Index: 551221 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0256. Min Range: -5.0256
Max Act: 4.4631. Min Act: -0.1700
Data Index: 5315364 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0256. Min Range: -5.0256
Max Act: 4.4631. Min Act: -0.1700
Data Index: 7833145 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0256. Min Range: -5.0256
Max Act: 4.4631. Min Act: -0.1700
Data Index: 4481398 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0256. Min Range: -5.0256
Max Act: 4.4318. Min Act: -0.1700
Data Index: 6135486 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0256. Min Range: -5.0256
Max Act: 4.4631. Min Act: -0.1700
Data Index: 4249433 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0256. Min Range: -5.0256
Max Act: 4.4318. Min Act: -0.1700
Data Index: 4846395 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0256. Min Range: -5.0256
Max Act: 4.4006. Min Act: -0.1700
Data Index: 54666 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0256. Min Range: -5.0256
Max Act: 4.4318. Min Act: -0.1700
Data Index: 4592064 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0256. Min Range: -5.0256
Max Act: 4.4006. Min Act: -0.1700
Data Index: 290114 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0256. Min Range: -5.0256
Max Act: 4.4318. Min Act: -0.1700
Data Index: 4777940 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0256. Min Range: -5.0256
Max Act: 4.4006. Min Act: -0.1700
Data Index: 737487 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0256. Min Range: -5.0256
Max Act: 4.4006. Min Act: -0.1700
Data Index: 1924319 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19