Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1665 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.2349. Min Range: -3.2349
Max Act: 3.2349. Min Act: -0.1700
Data Index: 132131 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2349. Min Range: -3.2349
Max Act: 3.2035. Min Act: -0.1700
Data Index: 354484 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2349. Min Range: -3.2349
Max Act: 3.1405. Min Act: -0.1700
Data Index: 1221187 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2349. Min Range: -3.2349
Max Act: 3.1878. Min Act: -0.1700
Data Index: 762885 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2349. Min Range: -3.2349
Max Act: 3.0775. Min Act: -0.1700
Data Index: 479356 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2349. Min Range: -3.2349
Max Act: 3.0932. Min Act: -0.1700
Data Index: 553564 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2349. Min Range: -3.2349
Max Act: 3.0617. Min Act: -0.1700
Data Index: 814900 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2349. Min Range: -3.2349
Max Act: 3.0932. Min Act: -0.1700
Data Index: 817198 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2349. Min Range: -3.2349
Max Act: 3.0459. Min Act: -0.1700
Data Index: 749511 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2349. Min Range: -3.2349
Max Act: 3.0301. Min Act: -0.1700
Data Index: 110679 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2349. Min Range: -3.2349
Max Act: 3.0301. Min Act: -0.1700
Data Index: 1050791 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2349. Min Range: -3.2349
Max Act: 2.9985. Min Act: -0.1700
Data Index: 727380 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2349. Min Range: -3.2349
Max Act: 2.9827. Min Act: -0.1700
Data Index: 1183264 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2349. Min Range: -3.2349
Max Act: 2.9827. Min Act: -0.1700
Data Index: 766855 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2349. Min Range: -3.2349
Max Act: 3.0143. Min Act: -0.1700
Data Index: 307640 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2349. Min Range: -3.2349
Max Act: 3.0143. Min Act: -0.1700
Data Index: 789737 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2349. Min Range: -3.2349
Max Act: 2.9669. Min Act: -0.1700
Data Index: 150903 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2349. Min Range: -3.2349
Max Act: 2.9669. Min Act: -0.1700
Data Index: 492656 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2349. Min Range: -3.2349
Max Act: 2.9985. Min Act: -0.1700
Data Index: 380821 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2349. Min Range: -3.2349
Max Act: 2.9669. Min Act: -0.1700
Data Index: 304493 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19