Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3958 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.8825. Min Act: -0.1700
Data Index: 6836273 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.8654. Min Act: -0.1700
Data Index: 4926482 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.8483. Min Act: -0.1700
Data Index: 3379113 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.8397. Min Act: -0.1700
Data Index: 1018845 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.8312. Min Act: -0.1700
Data Index: 5039985 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.8226. Min Act: -0.1700
Data Index: 6128488 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.8140. Min Act: -0.1700
Data Index: 4136738 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.8140. Min Act: -0.1700
Data Index: 8704768 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.8140. Min Act: -0.1700
Data Index: 6544181 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.8140. Min Act: -0.1700
Data Index: 112317 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.8054. Min Act: -0.1700
Data Index: 4033912 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.7968. Min Act: -0.1700
Data Index: 3575901 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.7968. Min Act: -0.1700
Data Index: 3728412 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.7796. Min Act: -0.1700
Data Index: 2862267 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.7623. Min Act: -0.1700
Data Index: 3753413 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.7537. Min Act: -0.1700
Data Index: 8145108 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.7537. Min Act: -0.1700
Data Index: 3009885 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.7537. Min Act: -0.1700
Data Index: 676916 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.7451. Min Act: -0.1700
Data Index: 7433749 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8825. Min Range: -1.8825
Max Act: 1.7537. Min Act: -0.1700
Data Index: 5966987 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19