Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3522 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2711. Min Range: -6.2711
Max Act: 6.2711. Min Act: -0.1700
Data Index: 3796829 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2711. Min Range: -6.2711
Max Act: 6.1148. Min Act: -0.1694
Data Index: 1252193 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2711. Min Range: -6.2711
Max Act: 6.0836. Min Act: -0.1700
Data Index: 8799485 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2711. Min Range: -6.2711
Max Act: 6.0211. Min Act: -0.1700
Data Index: 1986393 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2711. Min Range: -6.2711
Max Act: 6.0211. Min Act: -0.1700
Data Index: 4536974 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2711. Min Range: -6.2711
Max Act: 5.9898. Min Act: -0.1700
Data Index: 7065373 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2711. Min Range: -6.2711
Max Act: 5.9586. Min Act: -0.1700
Data Index: 1149558 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2711. Min Range: -6.2711
Max Act: 5.9586. Min Act: -0.1700
Data Index: 3037298 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2711. Min Range: -6.2711
Max Act: 5.9586. Min Act: -0.1700
Data Index: 7545675 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2711. Min Range: -6.2711
Max Act: 5.9586. Min Act: -0.1700
Data Index: 6595438 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2711. Min Range: -6.2711
Max Act: 5.9273. Min Act: -0.1700
Data Index: 1499719 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2711. Min Range: -6.2711
Max Act: 5.8961. Min Act: -0.1700
Data Index: 8041972 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2711. Min Range: -6.2711
Max Act: 5.9273. Min Act: -0.1700
Data Index: 1460015 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2711. Min Range: -6.2711
Max Act: 5.9273. Min Act: -0.1700
Data Index: 1797281 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2711. Min Range: -6.2711
Max Act: 5.9273. Min Act: -0.1700
Data Index: 7828754 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2711. Min Range: -6.2711
Max Act: 5.9273. Min Act: -0.1700
Data Index: 1206769 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2711. Min Range: -6.2711
Max Act: 5.9273. Min Act: -0.1700
Data Index: 3353319 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2711. Min Range: -6.2711
Max Act: 5.8961. Min Act: -0.1700
Data Index: 1361365 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2711. Min Range: -6.2711
Max Act: 5.8961. Min Act: -0.1700
Data Index: 4599502 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2711. Min Range: -6.2711
Max Act: 5.8961. Min Act: -0.1700
Data Index: 1894021 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19