Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6322 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4382. Min Range: -6.4382
Max Act: 6.4382. Min Act: -0.1700
Data Index: 130001 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4382. Min Range: -6.4382
Max Act: 6.2507. Min Act: -0.1700
Data Index: 4392813 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4382. Min Range: -6.4382
Max Act: 6.1257. Min Act: -0.1700
Data Index: 3601143 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4382. Min Range: -6.4382
Max Act: 6.0944. Min Act: -0.1700
Data Index: 3423435 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4382. Min Range: -6.4382
Max Act: 6.0632. Min Act: -0.1700
Data Index: 5819243 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4382. Min Range: -6.4382
Max Act: 6.0632. Min Act: -0.1700
Data Index: 7249876 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4382. Min Range: -6.4382
Max Act: 6.0319. Min Act: -0.1700
Data Index: 336691 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4382. Min Range: -6.4382
Max Act: 6.0007. Min Act: -0.1700
Data Index: 961785 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4382. Min Range: -6.4382
Max Act: 5.9694. Min Act: -0.1700
Data Index: 3575612 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4382. Min Range: -6.4382
Max Act: 5.9694. Min Act: -0.1700
Data Index: 8128232 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4382. Min Range: -6.4382
Max Act: 5.9694. Min Act: -0.1700
Data Index: 4244149 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4382. Min Range: -6.4382
Max Act: 5.9694. Min Act: -0.1700
Data Index: 2822037 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4382. Min Range: -6.4382
Max Act: 5.9382. Min Act: -0.1700
Data Index: 1708266 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4382. Min Range: -6.4382
Max Act: 5.9069. Min Act: -0.1700
Data Index: 6412706 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4382. Min Range: -6.4382
Max Act: 5.9382. Min Act: -0.1700
Data Index: 4114952 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4382. Min Range: -6.4382
Max Act: 5.9382. Min Act: -0.1700
Data Index: 5963238 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4382. Min Range: -6.4382
Max Act: 5.9069. Min Act: -0.1700
Data Index: 6746822 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4382. Min Range: -6.4382
Max Act: 5.9069. Min Act: -0.1700
Data Index: 7927594 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4382. Min Range: -6.4382
Max Act: 5.8757. Min Act: -0.1700
Data Index: 6819269 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4382. Min Range: -6.4382
Max Act: 5.8757. Min Act: -0.1700
Data Index: 6285533 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19