Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1870 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6446. Min Range: -7.6446
Max Act: 7.6446. Min Act: -0.1700
Data Index: 2192174 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6446. Min Range: -7.6446
Max Act: 6.8946. Min Act: -0.1700
Data Index: 4615798 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6446. Min Range: -7.6446
Max Act: 6.8008. Min Act: -0.1700
Data Index: 7038493 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6446. Min Range: -7.6446
Max Act: 6.8008. Min Act: -0.1700
Data Index: 8600578 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6446. Min Range: -7.6446
Max Act: 6.8008. Min Act: -0.1700
Data Index: 6024078 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6446. Min Range: -7.6446
Max Act: 6.7696. Min Act: -0.1700
Data Index: 6693780 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6446. Min Range: -7.6446
Max Act: 6.7383. Min Act: -0.1700
Data Index: 7455492 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6446. Min Range: -7.6446
Max Act: 6.7071. Min Act: -0.1700
Data Index: 846799 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6446. Min Range: -7.6446
Max Act: 6.7071. Min Act: -0.1700
Data Index: 5691502 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6446. Min Range: -7.6446
Max Act: 6.6758. Min Act: -0.1700
Data Index: 3471867 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6446. Min Range: -7.6446
Max Act: 6.6133. Min Act: -0.1700
Data Index: 3688726 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6446. Min Range: -7.6446
Max Act: 6.6446. Min Act: -0.1700
Data Index: 2330961 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6446. Min Range: -7.6446
Max Act: 6.6446. Min Act: -0.1700
Data Index: 8437267 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6446. Min Range: -7.6446
Max Act: 6.5821. Min Act: -0.1700
Data Index: 1937072 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6446. Min Range: -7.6446
Max Act: 6.6133. Min Act: -0.1700
Data Index: 2110402 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6446. Min Range: -7.6446
Max Act: 6.5508. Min Act: -0.1700
Data Index: 6820872 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6446. Min Range: -7.6446
Max Act: 6.5196. Min Act: -0.1700
Data Index: 6785232 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6446. Min Range: -7.6446
Max Act: 6.5508. Min Act: -0.1700
Data Index: 220052 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6446. Min Range: -7.6446
Max Act: 6.4883. Min Act: -0.1700
Data Index: 2052243 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6446. Min Range: -7.6446
Max Act: 6.4883. Min Act: -0.1700
Data Index: 6341302 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19