Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1461 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.8278. Min Act: -0.1700
Data Index: 3689237 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.7341. Min Act: -0.1700
Data Index: 5531764 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.7028. Min Act: -0.1700
Data Index: 2270675 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.5778. Min Act: -0.1700
Data Index: 4187875 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.5466. Min Act: -0.1700
Data Index: 7998089 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.5153. Min Act: -0.1700
Data Index: 8641786 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.5153. Min Act: -0.1700
Data Index: 8494691 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.4841. Min Act: -0.1700
Data Index: 7534382 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.4528. Min Act: -0.1700
Data Index: 5065596 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.4528. Min Act: -0.1700
Data Index: 4645408 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.4528. Min Act: -0.1700
Data Index: 6629599 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.4216. Min Act: -0.1700
Data Index: 185005 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.3903. Min Act: -0.1700
Data Index: 587864 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.3591. Min Act: -0.1700
Data Index: 4948370 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.3591. Min Act: -0.1700
Data Index: 6722735 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.3278. Min Act: -0.1700
Data Index: 1655049 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.3591. Min Act: -0.1700
Data Index: 6987417 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.3903. Min Act: -0.1700
Data Index: 2993513 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.3278. Min Act: -0.1700
Data Index: 5161126 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8278. Min Range: -7.8278
Max Act: 7.3278. Min Act: -0.1700
Data Index: 3004984 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19