Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.8424. Min Act: -0.1700
Data Index: 356737 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.8111. Min Act: -0.1700
Data Index: 349833 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.7174. Min Act: -0.1700
Data Index: 1245538 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.6861. Min Act: -0.1700
Data Index: 1216506 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.6549. Min Act: -0.1700
Data Index: 299574 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.6236. Min Act: -0.1700
Data Index: 472938 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.6549. Min Act: -0.1700
Data Index: 495987 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.6236. Min Act: -0.1700
Data Index: 1116932 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.6236. Min Act: -0.1700
Data Index: 1140838 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.5924. Min Act: -0.1700
Data Index: 34538 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.5299. Min Act: -0.1700
Data Index: 1228940 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.5924. Min Act: -0.1700
Data Index: 484414 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.5924. Min Act: -0.1700
Data Index: 271546 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.6549. Min Act: -0.1700
Data Index: 1053522 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.5924. Min Act: -0.1700
Data Index: 114413 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.5924. Min Act: -0.1700
Data Index: 175462 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.5924. Min Act: -0.1700
Data Index: 18742 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.6236. Min Act: -0.1700
Data Index: 647359 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.5924. Min Act: -0.1700
Data Index: 1053159 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8424. Min Range: -4.8424
Max Act: 4.5611. Min Act: -0.1700
Data Index: 1070912 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19