Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 60 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.7588. Min Act: -0.1700
Data Index: 5094706 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.7275. Min Act: -0.1700
Data Index: 5429414 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.6963. Min Act: -0.1700
Data Index: 1412425 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.6963. Min Act: -0.1700
Data Index: 1412424 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.6963. Min Act: -0.1700
Data Index: 615285 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.6650. Min Act: -0.1700
Data Index: 4338059 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.6337. Min Act: -0.1700
Data Index: 2962960 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.6337. Min Act: -0.1700
Data Index: 7930374 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.6024. Min Act: -0.1700
Data Index: 1776588 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.6024. Min Act: -0.1700
Data Index: 5203135 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.6024. Min Act: -0.1700
Data Index: 538722 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.5711. Min Act: -0.1700
Data Index: 8121204 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.5711. Min Act: -0.1700
Data Index: 1641484 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.5398. Min Act: -0.1700
Data Index: 4615285 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.5398. Min Act: -0.1700
Data Index: 7020305 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.5084. Min Act: -0.1700
Data Index: 5623071 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.5398. Min Act: -0.1700
Data Index: 71157 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.5398. Min Act: -0.1700
Data Index: 1906237 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.5398. Min Act: -0.1700
Data Index: 1906236 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7588. Min Range: -3.7588
Max Act: 3.5398. Min Act: -0.1700
Data Index: 838412 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19