Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6265 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2427. Min Range: -5.2427
Max Act: 5.2427. Min Act: -0.1700
Data Index: 200267 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2427. Min Range: -5.2427
Max Act: 5.0865. Min Act: -0.1700
Data Index: 3596678 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2427. Min Range: -5.2427
Max Act: 5.0552. Min Act: -0.1700
Data Index: 1997900 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2427. Min Range: -5.2427
Max Act: 5.0552. Min Act: -0.1700
Data Index: 1804524 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2427. Min Range: -5.2427
Max Act: 5.0552. Min Act: -0.1700
Data Index: 940379 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2427. Min Range: -5.2427
Max Act: 5.0552. Min Act: -0.1700
Data Index: 2498481 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2427. Min Range: -5.2427
Max Act: 4.9927. Min Act: -0.1700
Data Index: 2707915 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2427. Min Range: -5.2427
Max Act: 4.9615. Min Act: -0.1700
Data Index: 4753319 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2427. Min Range: -5.2427
Max Act: 4.9615. Min Act: -0.1700
Data Index: 4443046 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2427. Min Range: -5.2427
Max Act: 4.9615. Min Act: -0.1700
Data Index: 6479313 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2427. Min Range: -5.2427
Max Act: 4.9302. Min Act: -0.1700
Data Index: 2657285 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2427. Min Range: -5.2427
Max Act: 4.9615. Min Act: -0.1700
Data Index: 415949 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2427. Min Range: -5.2427
Max Act: 4.8990. Min Act: -0.1700
Data Index: 7563077 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2427. Min Range: -5.2427
Max Act: 4.8990. Min Act: -0.1700
Data Index: 3285694 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2427. Min Range: -5.2427
Max Act: 4.8990. Min Act: -0.1700
Data Index: 2657284 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2427. Min Range: -5.2427
Max Act: 4.8677. Min Act: -0.1700
Data Index: 4941975 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2427. Min Range: -5.2427
Max Act: 4.8677. Min Act: -0.1700
Data Index: 6459257 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2427. Min Range: -5.2427
Max Act: 4.8677. Min Act: -0.1700
Data Index: 3633306 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2427. Min Range: -5.2427
Max Act: 4.8677. Min Act: -0.1700
Data Index: 4692204 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2427. Min Range: -5.2427
Max Act: 4.8365. Min Act: -0.1700
Data Index: 6680634 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19