Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 251 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.5522. Min Act: -0.1700
Data Index: 7796951 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4739. Min Act: -0.1700
Data Index: 5547195 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4582. Min Act: -0.1700
Data Index: 7127024 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4582. Min Act: -0.1700
Data Index: 8713609 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4582. Min Act: -0.1700
Data Index: 570194 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4425. Min Act: -0.1700
Data Index: 8548147 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4269. Min Act: -0.1700
Data Index: 4128041 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4112. Min Act: -0.1700
Data Index: 4834251 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4112. Min Act: -0.1700
Data Index: 2970676 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.4112. Min Act: -0.1700
Data Index: 6811613 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.3798. Min Act: -0.1700
Data Index: 6238493 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.3798. Min Act: -0.1700
Data Index: 1665224 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.3798. Min Act: -0.1700
Data Index: 6309205 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.3798. Min Act: -0.1700
Data Index: 3363480 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.3641. Min Act: -0.1700
Data Index: 1366935 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.3484. Min Act: -0.1700
Data Index: 6979480 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.3641. Min Act: -0.1700
Data Index: 2777816 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.3641. Min Act: -0.1700
Data Index: 7094031 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.3641. Min Act: -0.1700
Data Index: 2307118 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5522. Min Range: -3.5522
Max Act: 3.3484. Min Act: -0.1700
Data Index: 7534358 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19