Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 10 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.5298. Min Act: -0.1700
Data Index: 10612 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.4985. Min Act: -0.1700
Data Index: 118573 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.4360. Min Act: -0.1700
Data Index: 1451803 (Python Code)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.4360. Min Act: -0.1700
Data Index: 466039 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.4985. Min Act: -0.1700
Data Index: 977389 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.4673. Min Act: -0.1700
Data Index: 955379 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.3735. Min Act: -0.1700
Data Index: 1126819 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.5298. Min Act: -0.1700
Data Index: 1200834 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.4360. Min Act: -0.1700
Data Index: 413719 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.4048. Min Act: -0.1700
Data Index: 347335 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.4048. Min Act: -0.1700
Data Index: 365600 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.4360. Min Act: -0.1700
Data Index: 1041463 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.4360. Min Act: -0.1700
Data Index: 394621 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.4360. Min Act: -0.1700
Data Index: 323457 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.4360. Min Act: -0.1700
Data Index: 112332 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.3423. Min Act: -0.1700
Data Index: 882593 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.4048. Min Act: -0.1700
Data Index: 887397 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.4048. Min Act: -0.1700
Data Index: 238700 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.4360. Min Act: -0.1700
Data Index: 528377 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5298. Min Range: -6.5298
Max Act: 6.4048. Min Act: -0.1700
Data Index: 565103 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19