Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3925 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.5044. Min Act: -0.1700
Data Index: 4662358 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.5044. Min Act: -0.1700
Data Index: 3396761 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.4419. Min Act: -0.1700
Data Index: 6724167 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.4732. Min Act: -0.1700
Data Index: 8040828 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.4732. Min Act: -0.1700
Data Index: 290598 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.4419. Min Act: -0.1700
Data Index: 2207788 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.4419. Min Act: -0.1700
Data Index: 8377039 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.3482. Min Act: -0.1700
Data Index: 6934728 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.2857. Min Act: -0.1700
Data Index: 3439800 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.3169. Min Act: -0.1700
Data Index: 87895 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.2544. Min Act: -0.1700
Data Index: 1167324 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.2544. Min Act: -0.1700
Data Index: 4150734 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.2544. Min Act: -0.1700
Data Index: 7152506 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.2232. Min Act: -0.1700
Data Index: 8452650 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.2232. Min Act: -0.1700
Data Index: 3145253 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.2232. Min Act: -0.1700
Data Index: 4234643 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.2232. Min Act: -0.1700
Data Index: 4143577 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.2232. Min Act: -0.1700
Data Index: 4951674 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.1919. Min Act: -0.1700
Data Index: 490018 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5044. Min Range: -6.5044
Max Act: 6.2232. Min Act: -0.1700
Data Index: 3091736 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19