Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2192 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9378. Min Range: -5.9378
Max Act: 5.9378. Min Act: -0.1700
Data Index: 1791624 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9378. Min Range: -5.9378
Max Act: 5.1565. Min Act: -0.1700
Data Index: 302481 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9378. Min Range: -5.9378
Max Act: 5.1253. Min Act: -0.1700
Data Index: 2419987 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9378. Min Range: -5.9378
Max Act: 5.0003. Min Act: -0.1700
Data Index: 5198740 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9378. Min Range: -5.9378
Max Act: 4.9378. Min Act: -0.1700
Data Index: 5223399 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9378. Min Range: -5.9378
Max Act: 4.7503. Min Act: -0.1700
Data Index: 2407062 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9378. Min Range: -5.9378
Max Act: 4.7190. Min Act: -0.1700
Data Index: 3728806 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9378. Min Range: -5.9378
Max Act: 4.7190. Min Act: -0.1700
Data Index: 4300113 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9378. Min Range: -5.9378
Max Act: 4.6878. Min Act: -0.1700
Data Index: 5090479 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9378. Min Range: -5.9378
Max Act: 4.6878. Min Act: -0.1700
Data Index: 7353995 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9378. Min Range: -5.9378
Max Act: 4.6878. Min Act: -0.1700
Data Index: 8601359 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9378. Min Range: -5.9378
Max Act: 4.6565. Min Act: -0.1700
Data Index: 2159583 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9378. Min Range: -5.9378
Max Act: 4.6565. Min Act: -0.1700
Data Index: 878511 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9378. Min Range: -5.9378
Max Act: 4.5940. Min Act: -0.1700
Data Index: 1785360 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9378. Min Range: -5.9378
Max Act: 4.5940. Min Act: -0.1700
Data Index: 1555360 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9378. Min Range: -5.9378
Max Act: 4.5940. Min Act: -0.1700
Data Index: 918476 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9378. Min Range: -5.9378
Max Act: 4.5940. Min Act: -0.1700
Data Index: 4355049 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9378. Min Range: -5.9378
Max Act: 4.5315. Min Act: -0.1700
Data Index: 771189 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9378. Min Range: -5.9378
Max Act: 4.5315. Min Act: -0.1700
Data Index: 3773902 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9378. Min Range: -5.9378
Max Act: 4.4690. Min Act: -0.1700
Data Index: 3980157 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19