Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4275 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5319. Min Range: -8.5319
Max Act: 8.5319. Min Act: -0.1700
Data Index: 2869057 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5319. Min Range: -8.5319
Max Act: 8.4069. Min Act: -0.1700
Data Index: 8466262 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5319. Min Range: -8.5319
Max Act: 8.1569. Min Act: -0.1700
Data Index: 1665816 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5319. Min Range: -8.5319
Max Act: 8.1569. Min Act: -0.1700
Data Index: 6493849 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5319. Min Range: -8.5319
Max Act: 8.0944. Min Act: -0.1700
Data Index: 4453874 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5319. Min Range: -8.5319
Max Act: 8.0944. Min Act: -0.1700
Data Index: 7991553 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5319. Min Range: -8.5319
Max Act: 8.0319. Min Act: -0.1700
Data Index: 2640467 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5319. Min Range: -8.5319
Max Act: 8.0319. Min Act: -0.1700
Data Index: 7757663 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5319. Min Range: -8.5319
Max Act: 8.0319. Min Act: -0.1700
Data Index: 1146591 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5319. Min Range: -8.5319
Max Act: 7.9694. Min Act: -0.1700
Data Index: 7920703 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5319. Min Range: -8.5319
Max Act: 7.9694. Min Act: -0.1700
Data Index: 60290 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5319. Min Range: -8.5319
Max Act: 7.9694. Min Act: -0.1700
Data Index: 6124360 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5319. Min Range: -8.5319
Max Act: 7.9694. Min Act: -0.1700
Data Index: 1061099 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5319. Min Range: -8.5319
Max Act: 7.9069. Min Act: -0.1700
Data Index: 2111502 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5319. Min Range: -8.5319
Max Act: 7.9069. Min Act: -0.1700
Data Index: 936173 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5319. Min Range: -8.5319
Max Act: 7.9069. Min Act: -0.1700
Data Index: 4522225 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5319. Min Range: -8.5319
Max Act: 7.9069. Min Act: -0.1700
Data Index: 7586922 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5319. Min Range: -8.5319
Max Act: 7.9069. Min Act: -0.1700
Data Index: 6358069 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5319. Min Range: -8.5319
Max Act: 7.8444. Min Act: -0.1700
Data Index: 1925564 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5319. Min Range: -8.5319
Max Act: 7.8444. Min Act: -0.1700
Data Index: 2785561 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19