Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3345 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.9008. Min Act: -0.1700
Data Index: 2598513 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.9008. Min Act: -0.1700
Data Index: 5828312 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.8383. Min Act: -0.1700
Data Index: 211363 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.7758. Min Act: -0.1700
Data Index: 7910704 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.7758. Min Act: -0.1700
Data Index: 6188327 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.7758. Min Act: -0.1700
Data Index: 7662732 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.7446. Min Act: -0.1700
Data Index: 4458466 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.7446. Min Act: -0.1700
Data Index: 8195500 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.7446. Min Act: -0.1700
Data Index: 1722610 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.7446. Min Act: -0.1700
Data Index: 3639960 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.7446. Min Act: -0.1700
Data Index: 6107706 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.7133. Min Act: -0.1700
Data Index: 2059057 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.7133. Min Act: -0.1700
Data Index: 1064510 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.7133. Min Act: -0.1700
Data Index: 1028538 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.7133. Min Act: -0.1700
Data Index: 2257281 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.6821. Min Act: -0.1700
Data Index: 2484561 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.6821. Min Act: -0.1700
Data Index: 5720204 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.6821. Min Act: -0.1700
Data Index: 5569003 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.6821. Min Act: -0.1700
Data Index: 435531 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9008. Min Range: -4.9008
Max Act: 4.6821. Min Act: -0.1700
Data Index: 7050761 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19