Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 44 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.5669. Min Range: -3.5669
Max Act: 3.5669. Min Act: -0.1700
Data Index: 1503346 (Python Code)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5669. Min Range: -3.5669
Max Act: 3.1115. Min Act: -0.1700
Data Index: 1207453 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5669. Min Range: -3.5669
Max Act: 3.0958. Min Act: -0.1700
Data Index: 1559318 (Python Code)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5669. Min Range: -3.5669
Max Act: 3.0169. Min Act: -0.1700
Data Index: 936290 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5669. Min Range: -3.5669
Max Act: 3.0800. Min Act: -0.1700
Data Index: 1192915 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5669. Min Range: -3.5669
Max Act: 3.0169. Min Act: -0.1700
Data Index: 1415772 (Python Code)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5669. Min Range: -3.5669
Max Act: 3.0169. Min Act: -0.1700
Data Index: 1120595 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5669. Min Range: -3.5669
Max Act: 3.0327. Min Act: -0.1700
Data Index: 610228 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5669. Min Range: -3.5669
Max Act: 3.0169. Min Act: -0.1700
Data Index: 648464 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5669. Min Range: -3.5669
Max Act: 2.9536. Min Act: -0.1700
Data Index: 287395 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5669. Min Range: -3.5669
Max Act: 2.8902. Min Act: -0.1700
Data Index: 342662 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5669. Min Range: -3.5669
Max Act: 2.9694. Min Act: -0.1700
Data Index: 475983 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5669. Min Range: -3.5669
Max Act: 2.9219. Min Act: -0.1700
Data Index: 255568 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5669. Min Range: -3.5669
Max Act: 2.8584. Min Act: -0.1700
Data Index: 1629081 (Python Code)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5669. Min Range: -3.5669
Max Act: 2.9219. Min Act: -0.1700
Data Index: 1650197 (Python Code)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5669. Min Range: -3.5669
Max Act: 2.9536. Min Act: -0.1700
Data Index: 651477 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5669. Min Range: -3.5669
Max Act: 2.9378. Min Act: -0.1700
Data Index: 200258 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5669. Min Range: -3.5669
Max Act: 2.8584. Min Act: -0.1700
Data Index: 273887 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5669. Min Range: -3.5669
Max Act: 2.9536. Min Act: -0.1700
Data Index: 819164 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5669. Min Range: -3.5669
Max Act: 2.9219. Min Act: -0.1700
Data Index: 269272 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19