Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 521 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.5398. Min Act: -0.1700
Data Index: 66556 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.5398. Min Act: -0.1700
Data Index: 128562 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.5236. Min Act: -0.1700
Data Index: 712978 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.4912. Min Act: -0.1700
Data Index: 766437 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.4750. Min Act: -0.1700
Data Index: 434152 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.4588. Min Act: -0.1700
Data Index: 660555 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.4263. Min Act: -0.1700
Data Index: 691423 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.4425. Min Act: -0.1700
Data Index: 1214470 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.4100. Min Act: -0.1700
Data Index: 1478169 (Python Code)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.4100. Min Act: -0.1700
Data Index: 1279684 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.4263. Min Act: -0.1700
Data Index: 975970 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.4100. Min Act: -0.1700
Data Index: 665607 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.4263. Min Act: -0.1700
Data Index: 215751 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.4263. Min Act: -0.1700
Data Index: 18368 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.4100. Min Act: -0.1700
Data Index: 537582 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.3937. Min Act: -0.1700
Data Index: 751857 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.4100. Min Act: -0.1700
Data Index: 825190 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.4100. Min Act: -0.1700
Data Index: 824752 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.3773. Min Act: -0.1700
Data Index: 257565 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5398. Min Range: -2.5398
Max Act: 2.3937. Min Act: -0.1700
Data Index: 727302 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19