Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3767 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2693. Min Range: -6.2693
Max Act: 6.2693. Min Act: -0.1700
Data Index: 620129 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2693. Min Range: -6.2693
Max Act: 6.2380. Min Act: -0.1700
Data Index: 3814112 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2693. Min Range: -6.2693
Max Act: 6.2380. Min Act: -0.1700
Data Index: 3080773 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2693. Min Range: -6.2693
Max Act: 6.2380. Min Act: -0.1700
Data Index: 1998465 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2693. Min Range: -6.2693
Max Act: 6.1755. Min Act: -0.1700
Data Index: 1943046 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2693. Min Range: -6.2693
Max Act: 6.1443. Min Act: -0.1700
Data Index: 6066131 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2693. Min Range: -6.2693
Max Act: 6.1443. Min Act: -0.1700
Data Index: 4487578 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2693. Min Range: -6.2693
Max Act: 6.0818. Min Act: -0.1700
Data Index: 1589459 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2693. Min Range: -6.2693
Max Act: 6.1130. Min Act: -0.1700
Data Index: 4188365 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2693. Min Range: -6.2693
Max Act: 6.0818. Min Act: -0.1700
Data Index: 7556271 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2693. Min Range: -6.2693
Max Act: 5.9880. Min Act: -0.1700
Data Index: 5289338 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2693. Min Range: -6.2693
Max Act: 5.9880. Min Act: -0.1700
Data Index: 666197 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2693. Min Range: -6.2693
Max Act: 5.9568. Min Act: -0.1700
Data Index: 3891659 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2693. Min Range: -6.2693
Max Act: 5.9568. Min Act: -0.1700
Data Index: 6464382 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2693. Min Range: -6.2693
Max Act: 5.8943. Min Act: -0.1700
Data Index: 872162 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2693. Min Range: -6.2693
Max Act: 5.9255. Min Act: -0.1700
Data Index: 2362446 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2693. Min Range: -6.2693
Max Act: 5.8943. Min Act: -0.1700
Data Index: 4793974 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2693. Min Range: -6.2693
Max Act: 5.9255. Min Act: -0.1700
Data Index: 109073 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2693. Min Range: -6.2693
Max Act: 5.8630. Min Act: -0.1700
Data Index: 1576434 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2693. Min Range: -6.2693
Max Act: 5.8630. Min Act: -0.1700
Data Index: 4054182 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19