Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1689 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2481. Min Range: -5.2481
Max Act: 5.2481. Min Act: -0.1700
Data Index: 349612 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2481. Min Range: -5.2481
Max Act: 5.2481. Min Act: -0.1700
Data Index: 7863868 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2481. Min Range: -5.2481
Max Act: 5.2481. Min Act: -0.1700
Data Index: 7973246 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2481. Min Range: -5.2481
Max Act: 5.2481. Min Act: -0.1700
Data Index: 6127742 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2481. Min Range: -5.2481
Max Act: 5.2169. Min Act: -0.1700
Data Index: 2433395 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2481. Min Range: -5.2481
Max Act: 5.1544. Min Act: -0.1700
Data Index: 8198690 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2481. Min Range: -5.2481
Max Act: 5.1231. Min Act: -0.1700
Data Index: 6896136 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2481. Min Range: -5.2481
Max Act: 5.1231. Min Act: -0.1700
Data Index: 2495823 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2481. Min Range: -5.2481
Max Act: 5.0919. Min Act: -0.1700
Data Index: 141511 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2481. Min Range: -5.2481
Max Act: 5.0606. Min Act: -0.1700
Data Index: 7321348 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2481. Min Range: -5.2481
Max Act: 5.0294. Min Act: -0.1700
Data Index: 6361968 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2481. Min Range: -5.2481
Max Act: 5.0606. Min Act: -0.1700
Data Index: 6302150 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2481. Min Range: -5.2481
Max Act: 5.0606. Min Act: -0.1700
Data Index: 1437770 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2481. Min Range: -5.2481
Max Act: 5.0606. Min Act: -0.1700
Data Index: 213677 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2481. Min Range: -5.2481
Max Act: 5.0606. Min Act: -0.1700
Data Index: 2143991 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2481. Min Range: -5.2481
Max Act: 5.0294. Min Act: -0.1700
Data Index: 8005490 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2481. Min Range: -5.2481
Max Act: 5.0294. Min Act: -0.1700
Data Index: 7056689 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2481. Min Range: -5.2481
Max Act: 4.9981. Min Act: -0.1700
Data Index: 6003111 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2481. Min Range: -5.2481
Max Act: 4.9981. Min Act: -0.1700
Data Index: 4385379 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2481. Min Range: -5.2481
Max Act: 4.9981. Min Act: -0.1700
Data Index: 5539007 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19