Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3954 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.8195. Min Act: -0.1700
Data Index: 5253388 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.7882. Min Act: -0.1700
Data Index: 8588913 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.6632. Min Act: -0.1700
Data Index: 2446393 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.6632. Min Act: -0.1700
Data Index: 6550671 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.6632. Min Act: -0.1700
Data Index: 4989963 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.6632. Min Act: -0.1700
Data Index: 6667788 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.6632. Min Act: -0.1700
Data Index: 916688 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.6007. Min Act: -0.1700
Data Index: 5682027 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.6007. Min Act: -0.1700
Data Index: 3624334 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.5695. Min Act: -0.1700
Data Index: 2147932 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.5695. Min Act: -0.1700
Data Index: 6622547 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.5382. Min Act: -0.1700
Data Index: 8185702 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.5382. Min Act: -0.1700
Data Index: 7855496 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.5382. Min Act: -0.1700
Data Index: 4892629 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.5382. Min Act: -0.1700
Data Index: 4823083 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.5382. Min Act: -0.1700
Data Index: 1966324 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.5070. Min Act: -0.1700
Data Index: 863745 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.5070. Min Act: -0.1700
Data Index: 6792873 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.5070. Min Act: -0.1700
Data Index: 1464250 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8195. Min Range: -5.8195
Max Act: 5.5070. Min Act: -0.1700
Data Index: 4489596 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19