Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2020 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0024. Min Range: -7.0024
Max Act: 7.0024. Min Act: -0.1700
Data Index: 3482601 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0024. Min Range: -7.0024
Max Act: 7.0024. Min Act: -0.1700
Data Index: 7209235 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0024. Min Range: -7.0024
Max Act: 7.0024. Min Act: -0.1700
Data Index: 433582 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0024. Min Range: -7.0024
Max Act: 7.0024. Min Act: -0.1700
Data Index: 5525873 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0024. Min Range: -7.0024
Max Act: 6.9086. Min Act: -0.1700
Data Index: 7119858 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0024. Min Range: -7.0024
Max Act: 6.9399. Min Act: -0.1700
Data Index: 4571014 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0024. Min Range: -7.0024
Max Act: 6.8149. Min Act: -0.1700
Data Index: 7749102 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0024. Min Range: -7.0024
Max Act: 6.8149. Min Act: -0.1700
Data Index: 1615202 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0024. Min Range: -7.0024
Max Act: 6.8461. Min Act: -0.1700
Data Index: 4644153 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0024. Min Range: -7.0024
Max Act: 6.7836. Min Act: -0.1700
Data Index: 1338042 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0024. Min Range: -7.0024
Max Act: 6.7524. Min Act: -0.1700
Data Index: 3812070 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0024. Min Range: -7.0024
Max Act: 6.7211. Min Act: -0.1700
Data Index: 2244295 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0024. Min Range: -7.0024
Max Act: 6.7211. Min Act: -0.1700
Data Index: 7939477 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0024. Min Range: -7.0024
Max Act: 6.7524. Min Act: -0.1700
Data Index: 1988607 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0024. Min Range: -7.0024
Max Act: 6.7211. Min Act: -0.1700
Data Index: 1211817 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0024. Min Range: -7.0024
Max Act: 6.6899. Min Act: -0.1700
Data Index: 2731990 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0024. Min Range: -7.0024
Max Act: 6.7211. Min Act: -0.1700
Data Index: 621299 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0024. Min Range: -7.0024
Max Act: 6.7211. Min Act: -0.1700
Data Index: 4562781 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0024. Min Range: -7.0024
Max Act: 6.7211. Min Act: -0.1700
Data Index: 511238 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0024. Min Range: -7.0024
Max Act: 6.6899. Min Act: -0.1700
Data Index: 3109232 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19