Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2011 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.0360. Min Range: -6.0360
Max Act: 6.0360. Min Act: -0.1700
Data Index: 975201 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0360. Min Range: -6.0360
Max Act: 5.9423. Min Act: -0.1700
Data Index: 702493 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0360. Min Range: -6.0360
Max Act: 5.9110. Min Act: -0.1700
Data Index: 707327 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0360. Min Range: -6.0360
Max Act: 5.9423. Min Act: -0.1700
Data Index: 457771 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0360. Min Range: -6.0360
Max Act: 5.8173. Min Act: -0.1700
Data Index: 206918 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0360. Min Range: -6.0360
Max Act: 5.7235. Min Act: -0.1700
Data Index: 586993 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0360. Min Range: -6.0360
Max Act: 5.6610. Min Act: -0.1700
Data Index: 787269 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0360. Min Range: -6.0360
Max Act: 5.6923. Min Act: -0.1700
Data Index: 217177 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0360. Min Range: -6.0360
Max Act: 5.6298. Min Act: -0.1700
Data Index: 904232 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0360. Min Range: -6.0360
Max Act: 5.5673. Min Act: -0.1700
Data Index: 454258 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0360. Min Range: -6.0360
Max Act: 5.6298. Min Act: -0.1700
Data Index: 460460 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0360. Min Range: -6.0360
Max Act: 5.5360. Min Act: -0.1700
Data Index: 1311625 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0360. Min Range: -6.0360
Max Act: 5.5360. Min Act: -0.1700
Data Index: 19938 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0360. Min Range: -6.0360
Max Act: 5.5048. Min Act: -0.1700
Data Index: 955243 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0360. Min Range: -6.0360
Max Act: 5.5360. Min Act: -0.1700
Data Index: 1250917 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0360. Min Range: -6.0360
Max Act: 5.5048. Min Act: -0.1700
Data Index: 1512490 (Python Code)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0360. Min Range: -6.0360
Max Act: 5.4735. Min Act: -0.1700
Data Index: 1319263 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0360. Min Range: -6.0360
Max Act: 5.4423. Min Act: -0.1700
Data Index: 309288 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0360. Min Range: -6.0360
Max Act: 5.4735. Min Act: -0.1700
Data Index: 207534 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0360. Min Range: -6.0360
Max Act: 5.4423. Min Act: -0.1700
Data Index: 194377 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19