Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3927 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4611. Min Range: -6.4611
Max Act: 6.4611. Min Act: -0.1700
Data Index: 6469893 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4611. Min Range: -6.4611
Max Act: 6.3048. Min Act: -0.1700
Data Index: 2508101 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4611. Min Range: -6.4611
Max Act: 6.3048. Min Act: -0.1700
Data Index: 4681534 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4611. Min Range: -6.4611
Max Act: 6.2423. Min Act: -0.1700
Data Index: 3280409 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4611. Min Range: -6.4611
Max Act: 6.2111. Min Act: -0.1700
Data Index: 291950 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4611. Min Range: -6.4611
Max Act: 6.1798. Min Act: -0.1700
Data Index: 4524044 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4611. Min Range: -6.4611
Max Act: 6.1798. Min Act: -0.1700
Data Index: 5555659 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4611. Min Range: -6.4611
Max Act: 6.1798. Min Act: -0.1700
Data Index: 1749825 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4611. Min Range: -6.4611
Max Act: 6.1486. Min Act: -0.1700
Data Index: 521347 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4611. Min Range: -6.4611
Max Act: 6.1486. Min Act: -0.1700
Data Index: 1298347 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4611. Min Range: -6.4611
Max Act: 6.0861. Min Act: -0.1700
Data Index: 4124897 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4611. Min Range: -6.4611
Max Act: 6.0861. Min Act: -0.1700
Data Index: 604707 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4611. Min Range: -6.4611
Max Act: 6.0861. Min Act: -0.1700
Data Index: 1892868 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4611. Min Range: -6.4611
Max Act: 6.0236. Min Act: -0.1700
Data Index: 7934234 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4611. Min Range: -6.4611
Max Act: 6.0548. Min Act: -0.1700
Data Index: 376535 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4611. Min Range: -6.4611
Max Act: 6.0548. Min Act: -0.1700
Data Index: 1749466 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4611. Min Range: -6.4611
Max Act: 6.0236. Min Act: -0.1700
Data Index: 2781503 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4611. Min Range: -6.4611
Max Act: 6.0236. Min Act: -0.1700
Data Index: 6288361 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4611. Min Range: -6.4611
Max Act: 6.0236. Min Act: -0.1700
Data Index: 1119224 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4611. Min Range: -6.4611
Max Act: 5.9923. Min Act: -0.1700
Data Index: 2442318 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19