Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1760 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3442. Min Range: -8.3442
Max Act: 8.3442. Min Act: -0.1700
Data Index: 4696833 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3442. Min Range: -8.3442
Max Act: 8.1567. Min Act: -0.1700
Data Index: 2500008 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3442. Min Range: -8.3442
Max Act: 8.0942. Min Act: -0.1700
Data Index: 5924693 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3442. Min Range: -8.3442
Max Act: 8.0317. Min Act: -0.1700
Data Index: 1379712 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3442. Min Range: -8.3442
Max Act: 7.9692. Min Act: -0.1700
Data Index: 1177301 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3442. Min Range: -8.3442
Max Act: 7.9692. Min Act: -0.1700
Data Index: 2990656 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3442. Min Range: -8.3442
Max Act: 7.9380. Min Act: -0.1700
Data Index: 1524170 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3442. Min Range: -8.3442
Max Act: 7.8442. Min Act: -0.1700
Data Index: 1049483 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3442. Min Range: -8.3442
Max Act: 7.8130. Min Act: -0.1700
Data Index: 2780479 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3442. Min Range: -8.3442
Max Act: 7.7505. Min Act: -0.1700
Data Index: 4984189 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3442. Min Range: -8.3442
Max Act: 7.7505. Min Act: -0.1700
Data Index: 5417925 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3442. Min Range: -8.3442
Max Act: 7.7192. Min Act: -0.1700
Data Index: 1666126 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3442. Min Range: -8.3442
Max Act: 7.7192. Min Act: -0.1700
Data Index: 7091039 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3442. Min Range: -8.3442
Max Act: 7.7192. Min Act: -0.1700
Data Index: 4059636 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3442. Min Range: -8.3442
Max Act: 7.6880. Min Act: -0.1700
Data Index: 7086554 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3442. Min Range: -8.3442
Max Act: 7.6880. Min Act: -0.1700
Data Index: 2421993 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3442. Min Range: -8.3442
Max Act: 7.6880. Min Act: -0.1700
Data Index: 2827863 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3442. Min Range: -8.3442
Max Act: 7.6880. Min Act: -0.1700
Data Index: 3812828 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3442. Min Range: -8.3442
Max Act: 7.6880. Min Act: -0.1700
Data Index: 1184970 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3442. Min Range: -8.3442
Max Act: 7.6880. Min Act: -0.1700
Data Index: 6680110 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19