Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2519 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.8061. Min Act: -0.1700
Data Index: 8313953 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.7436. Min Act: -0.1700
Data Index: 3704582 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.4936. Min Act: -0.1700
Data Index: 6661026 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.4936. Min Act: -0.1700
Data Index: 2693612 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.4936. Min Act: -0.1700
Data Index: 708204 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.4311. Min Act: -0.1700
Data Index: 6957172 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.3686. Min Act: -0.1700
Data Index: 2360120 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.4311. Min Act: -0.1700
Data Index: 69564 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.3061. Min Act: -0.1700
Data Index: 5295568 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.3061. Min Act: -0.1700
Data Index: 6772176 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.3061. Min Act: -0.1700
Data Index: 5501198 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.2436. Min Act: -0.1700
Data Index: 4580530 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.2436. Min Act: -0.1700
Data Index: 1572012 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.2436. Min Act: -0.1700
Data Index: 7124381 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.3061. Min Act: -0.1700
Data Index: 8012156 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.2436. Min Act: -0.1700
Data Index: 6364904 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.2436. Min Act: -0.1700
Data Index: 69837 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.1811. Min Act: -0.1700
Data Index: 5833082 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.1186. Min Act: -0.1700
Data Index: 215030 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8061. Min Range: -8.8061
Max Act: 8.1186. Min Act: -0.1700
Data Index: 1157966 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19