Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1543 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.9195. Min Act: -0.1700
Data Index: 407905 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.8258. Min Act: -0.1700
Data Index: 5456855 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.7945. Min Act: -0.1700
Data Index: 4300823 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.7320. Min Act: -0.1700
Data Index: 2567697 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.7320. Min Act: -0.1700
Data Index: 7558866 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.6695. Min Act: -0.1700
Data Index: 3944993 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.6695. Min Act: -0.1700
Data Index: 4224734 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.6383. Min Act: -0.1700
Data Index: 6117451 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.6383. Min Act: -0.1700
Data Index: 1184515 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.6070. Min Act: -0.1700
Data Index: 1511275 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.6070. Min Act: -0.1700
Data Index: 1965354 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.6070. Min Act: -0.1700
Data Index: 1905109 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.6070. Min Act: -0.1700
Data Index: 1758092 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.5758. Min Act: -0.1700
Data Index: 8334809 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.5758. Min Act: -0.1700
Data Index: 774654 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.5758. Min Act: -0.1700
Data Index: 5310125 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.5758. Min Act: -0.1700
Data Index: 6512437 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.5445. Min Act: -0.1700
Data Index: 6173467 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.5445. Min Act: -0.1700
Data Index: 2336825 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9195. Min Range: -6.9195
Max Act: 6.5133. Min Act: -0.1700
Data Index: 3157463 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19