Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5549 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.1783. Min Range: -17.1783
Max Act: 17.1783. Min Act: -0.1700
Data Index: 967206 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.1783. Min Range: -17.1783
Max Act: 15.8033. Min Act: -0.1700
Data Index: 2018404 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.1783. Min Range: -17.1783
Max Act: 15.1158. Min Act: -0.1700
Data Index: 2303512 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.1783. Min Range: -17.1783
Max Act: 15.1158. Min Act: -0.1700
Data Index: 5429316 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.1783. Min Range: -17.1783
Max Act: 15.0533. Min Act: -0.1700
Data Index: 8211588 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.1783. Min Range: -17.1783
Max Act: 15.0533. Min Act: -0.1700
Data Index: 1286976 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.1783. Min Range: -17.1783
Max Act: 14.9908. Min Act: -0.1700
Data Index: 3481218 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.1783. Min Range: -17.1783
Max Act: 14.9908. Min Act: -0.1700
Data Index: 3855246 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.1783. Min Range: -17.1783
Max Act: 14.9283. Min Act: -0.1700
Data Index: 3797681 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.1783. Min Range: -17.1783
Max Act: 14.9283. Min Act: -0.1700
Data Index: 8772030 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.1783. Min Range: -17.1783
Max Act: 14.8658. Min Act: -0.1700
Data Index: 283642 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.1783. Min Range: -17.1783
Max Act: 14.8658. Min Act: -0.1700
Data Index: 633990 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.1783. Min Range: -17.1783
Max Act: 14.8658. Min Act: -0.1700
Data Index: 4201580 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.1783. Min Range: -17.1783
Max Act: 14.8033. Min Act: -0.1700
Data Index: 5673341 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.1783. Min Range: -17.1783
Max Act: 14.8033. Min Act: -0.1699
Data Index: 328445 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.1783. Min Range: -17.1783
Max Act: 14.7408. Min Act: -0.1700
Data Index: 6805418 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.1783. Min Range: -17.1783
Max Act: 14.7408. Min Act: -0.1700
Data Index: 1320822 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.1783. Min Range: -17.1783
Max Act: 14.7408. Min Act: -0.1700
Data Index: 7747377 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.1783. Min Range: -17.1783
Max Act: 14.6783. Min Act: -0.1700
Data Index: 1211535 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.1783. Min Range: -17.1783
Max Act: 14.6783. Min Act: -0.1700
Data Index: 2216779 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19