Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2021 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2381. Min Range: -7.2381
Max Act: 7.2381. Min Act: -0.1700
Data Index: 2541323 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2381. Min Range: -7.2381
Max Act: 7.1756. Min Act: -0.1700
Data Index: 4816327 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2381. Min Range: -7.2381
Max Act: 7.1756. Min Act: -0.1700
Data Index: 8050179 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2381. Min Range: -7.2381
Max Act: 7.1756. Min Act: -0.1700
Data Index: 1830797 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2381. Min Range: -7.2381
Max Act: 7.0818. Min Act: -0.1700
Data Index: 8433019 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2381. Min Range: -7.2381
Max Act: 7.0193. Min Act: -0.1700
Data Index: 3684065 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2381. Min Range: -7.2381
Max Act: 6.9881. Min Act: -0.1700
Data Index: 6332999 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2381. Min Range: -7.2381
Max Act: 6.9256. Min Act: -0.1700
Data Index: 5847010 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2381. Min Range: -7.2381
Max Act: 6.8631. Min Act: -0.1700
Data Index: 5499930 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2381. Min Range: -7.2381
Max Act: 6.8318. Min Act: -0.1700
Data Index: 3153843 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2381. Min Range: -7.2381
Max Act: 6.8631. Min Act: -0.1700
Data Index: 2266035 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2381. Min Range: -7.2381
Max Act: 6.8631. Min Act: -0.1700
Data Index: 8668834 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2381. Min Range: -7.2381
Max Act: 6.8318. Min Act: -0.1700
Data Index: 71969 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2381. Min Range: -7.2381
Max Act: 6.8006. Min Act: -0.1700
Data Index: 6499472 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2381. Min Range: -7.2381
Max Act: 6.7693. Min Act: -0.1700
Data Index: 2450355 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2381. Min Range: -7.2381
Max Act: 6.7693. Min Act: -0.1700
Data Index: 4349951 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2381. Min Range: -7.2381
Max Act: 6.7381. Min Act: -0.1700
Data Index: 606712 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2381. Min Range: -7.2381
Max Act: 6.7693. Min Act: -0.1700
Data Index: 5310216 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2381. Min Range: -7.2381
Max Act: 6.7068. Min Act: -0.1700
Data Index: 6885367 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2381. Min Range: -7.2381
Max Act: 6.7068. Min Act: -0.1700
Data Index: 766366 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19