Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.7285. Min Act: -0.1700
Data Index: 1578829 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.6660. Min Act: -0.1700
Data Index: 3752244 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.4472. Min Act: -0.1700
Data Index: 4926425 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.3847. Min Act: -0.1700
Data Index: 499458 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.3535. Min Act: -0.1700
Data Index: 1614583 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.3222. Min Act: -0.1700
Data Index: 935805 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.3222. Min Act: -0.1700
Data Index: 4090512 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.3222. Min Act: -0.1700
Data Index: 5667658 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.3222. Min Act: -0.1700
Data Index: 4214068 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.3535. Min Act: -0.1700
Data Index: 3191985 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.2910. Min Act: -0.1700
Data Index: 3348396 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.3222. Min Act: -0.1700
Data Index: 7530643 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.3222. Min Act: -0.1700
Data Index: 4945021 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.3222. Min Act: -0.1700
Data Index: 5593405 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.2910. Min Act: -0.1700
Data Index: 4487800 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.2910. Min Act: -0.1700
Data Index: 2653411 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.2597. Min Act: -0.1700
Data Index: 6757862 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.2597. Min Act: -0.1700
Data Index: 7309807 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.2285. Min Act: -0.1700
Data Index: 1535469 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7285. Min Range: -5.7285
Max Act: 5.2597. Min Act: -0.1700
Data Index: 7022207 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19