Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2839 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.6928. Min Act: -0.1700
Data Index: 5862536 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.6303. Min Act: -0.1700
Data Index: 1704091 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.6303. Min Act: -0.1700
Data Index: 6493604 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.6303. Min Act: -0.1700
Data Index: 4001434 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.5365. Min Act: -0.1700
Data Index: 3680138 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.5053. Min Act: -0.1699
Data Index: 2517666 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.5053. Min Act: -0.1700
Data Index: 1831305 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.5365. Min Act: -0.1700
Data Index: 6342743 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.5053. Min Act: -0.1700
Data Index: 4344682 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4740. Min Act: -0.1700
Data Index: 6833991 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4740. Min Act: -0.1700
Data Index: 8247558 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4428. Min Act: -0.1700
Data Index: 6647294 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4428. Min Act: -0.1700
Data Index: 7860304 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4428. Min Act: -0.1700
Data Index: 1420776 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4115. Min Act: -0.1700
Data Index: 7618732 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4115. Min Act: -0.1700
Data Index: 2550070 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4428. Min Act: -0.1695
Data Index: 2327353 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4115. Min Act: -0.1700
Data Index: 1575058 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4428. Min Act: -0.1699
Data Index: 8731297 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4115. Min Act: -0.1700
Data Index: 740990 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19