Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3346 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2918. Min Range: -6.2918
Max Act: 6.2918. Min Act: -0.1700
Data Index: 1213730 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2918. Min Range: -6.2918
Max Act: 6.1981. Min Act: -0.1700
Data Index: 2923892 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2918. Min Range: -6.2918
Max Act: 6.0106. Min Act: -0.1700
Data Index: 1798748 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2918. Min Range: -6.2918
Max Act: 5.8231. Min Act: -0.1700
Data Index: 7982168 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2918. Min Range: -6.2918
Max Act: 5.7918. Min Act: -0.1700
Data Index: 4728955 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2918. Min Range: -6.2918
Max Act: 5.7606. Min Act: -0.1700
Data Index: 5577461 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2918. Min Range: -6.2918
Max Act: 5.6043. Min Act: -0.1700
Data Index: 1661120 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2918. Min Range: -6.2918
Max Act: 5.5418. Min Act: -0.1700
Data Index: 7064912 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2918. Min Range: -6.2918
Max Act: 5.5418. Min Act: -0.1700
Data Index: 7655856 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2918. Min Range: -6.2918
Max Act: 5.5106. Min Act: -0.1700
Data Index: 8551538 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2918. Min Range: -6.2918
Max Act: 5.5106. Min Act: -0.1700
Data Index: 6517752 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2918. Min Range: -6.2918
Max Act: 5.4793. Min Act: -0.1700
Data Index: 2965563 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2918. Min Range: -6.2918
Max Act: 5.4793. Min Act: -0.1700
Data Index: 2626419 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2918. Min Range: -6.2918
Max Act: 5.4481. Min Act: -0.1700
Data Index: 2126038 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2918. Min Range: -6.2918
Max Act: 5.4168. Min Act: -0.1700
Data Index: 6548474 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2918. Min Range: -6.2918
Max Act: 5.4168. Min Act: -0.1700
Data Index: 4700463 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2918. Min Range: -6.2918
Max Act: 5.3856. Min Act: -0.1700
Data Index: 4653678 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2918. Min Range: -6.2918
Max Act: 5.3856. Min Act: -0.1700
Data Index: 1123107 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2918. Min Range: -6.2918
Max Act: 5.3543. Min Act: -0.1700
Data Index: 1123103 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2918. Min Range: -6.2918
Max Act: 5.3231. Min Act: -0.1700
Data Index: 487765 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19