Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1994 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.6577. Min Act: -0.1700
Data Index: 1225675 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.4859. Min Act: -0.1700
Data Index: 484797 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.4390. Min Act: -0.1700
Data Index: 702512 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.4390. Min Act: -0.1700
Data Index: 67501 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.3452. Min Act: -0.1700
Data Index: 1108614 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.3296. Min Act: -0.1700
Data Index: 222240 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.3140. Min Act: -0.1700
Data Index: 1264751 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.3452. Min Act: -0.1700
Data Index: 96491 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.3296. Min Act: -0.1700
Data Index: 880950 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.3140. Min Act: -0.1700
Data Index: 383367 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.3765. Min Act: -0.1700
Data Index: 716794 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.3296. Min Act: -0.1700
Data Index: 1175643 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.2827. Min Act: -0.1700
Data Index: 461651 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.3140. Min Act: -0.1700
Data Index: 470745 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.2827. Min Act: -0.1700
Data Index: 221377 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.3140. Min Act: -0.1700
Data Index: 847402 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.2827. Min Act: -0.1700
Data Index: 236661 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.2827. Min Act: -0.1700
Data Index: 628020 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.2983. Min Act: -0.1700
Data Index: 481523 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6577. Min Range: -4.6577
Max Act: 4.2202. Min Act: -0.1700
Data Index: 1171401 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19