Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2026 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.7428. Min Act: -0.1700
Data Index: 18633 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.7740. Min Act: -0.1700
Data Index: 682250 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.7428. Min Act: -0.1700
Data Index: 29608 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.6178. Min Act: -0.1700
Data Index: 1285452 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.5865. Min Act: -0.1700
Data Index: 441656 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.5865. Min Act: -0.1700
Data Index: 1226415 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.6178. Min Act: -0.1700
Data Index: 681995 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.5553. Min Act: -0.1700
Data Index: 412983 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.5553. Min Act: -0.1700
Data Index: 279780 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.5240. Min Act: -0.1700
Data Index: 1249310 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.4615. Min Act: -0.1700
Data Index: 913264 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.5240. Min Act: -0.1700
Data Index: 731361 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.4928. Min Act: -0.1700
Data Index: 1371915 (Python Code)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.4615. Min Act: -0.1700
Data Index: 1432179 (Python Code)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.4928. Min Act: -0.1700
Data Index: 283790 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.5240. Min Act: -0.1700
Data Index: 634316 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.4928. Min Act: -0.1700
Data Index: 273340 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.4928. Min Act: -0.1700
Data Index: 494349 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.4928. Min Act: -0.1700
Data Index: 329502 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7740. Min Range: -4.7740
Max Act: 4.4928. Min Act: -0.1700
Data Index: 308102 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19