Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6340 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.4339. Min Act: -0.1700
Data Index: 1188984 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.2776. Min Act: -0.1700
Data Index: 3813254 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.2464. Min Act: -0.1700
Data Index: 4858706 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.2464. Min Act: -0.1700
Data Index: 7022908 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.2151. Min Act: -0.1700
Data Index: 6989765 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.2464. Min Act: -0.1700
Data Index: 1799414 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.2151. Min Act: -0.1700
Data Index: 8585592 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.1526. Min Act: -0.1700
Data Index: 7609785 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.1839. Min Act: -0.1700
Data Index: 1237191 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.1526. Min Act: -0.1700
Data Index: 4974932 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.1526. Min Act: -0.1700
Data Index: 3533502 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.1526. Min Act: -0.1700
Data Index: 935190 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.1526. Min Act: -0.1700
Data Index: 815476 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.1526. Min Act: -0.1700
Data Index: 3816709 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.1214. Min Act: -0.1700
Data Index: 1692869 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.1526. Min Act: -0.1700
Data Index: 4868437 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.1526. Min Act: -0.1700
Data Index: 690695 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.1214. Min Act: -0.1700
Data Index: 5340201 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.1214. Min Act: -0.1700
Data Index: 3503656 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4339. Min Range: -6.4339
Max Act: 6.1214. Min Act: -0.1700
Data Index: 1400640 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19