Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3650 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.9196. Min Act: -0.1700
Data Index: 7560731 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.8571. Min Act: -0.1699
Data Index: 2612356 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.5759. Min Act: -0.1700
Data Index: 1125566 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.5446. Min Act: -0.1700
Data Index: 8780297 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.5446. Min Act: -0.1700
Data Index: 8338748 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.5134. Min Act: -0.1700
Data Index: 8016030 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.5134. Min Act: -0.1700
Data Index: 696833 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.4821. Min Act: -0.1700
Data Index: 1995029 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.4821. Min Act: -0.1700
Data Index: 484616 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.4509. Min Act: -0.1700
Data Index: 4659969 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.4196. Min Act: -0.1696
Data Index: 3021114 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.4196. Min Act: -0.1700
Data Index: 3408770 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.3571. Min Act: -0.1700
Data Index: 6910093 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.3884. Min Act: -0.1700
Data Index: 2315096 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.3884. Min Act: -0.1700
Data Index: 2162408 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.3884. Min Act: -0.1700
Data Index: 4269259 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.3884. Min Act: -0.1700
Data Index: 2354686 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.3884. Min Act: -0.1700
Data Index: 2023216 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.3884. Min Act: -0.1699
Data Index: 8704139 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9196. Min Range: -5.9196
Max Act: 5.3884. Min Act: -0.1700
Data Index: 3359295 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19