Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 404 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.7734. Min Act: -0.1700
Data Index: 787085 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.7109. Min Act: -0.1700
Data Index: 790858 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.5859. Min Act: -0.1700
Data Index: 1140398 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.5234. Min Act: -0.1700
Data Index: 315672 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.5234. Min Act: -0.1700
Data Index: 791466 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.5234. Min Act: -0.1700
Data Index: 472272 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.5234. Min Act: -0.1700
Data Index: 222520 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.4296. Min Act: -0.1700
Data Index: 1000407 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.4296. Min Act: -0.1700
Data Index: 186701 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.4296. Min Act: -0.1700
Data Index: 434607 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.4921. Min Act: -0.1700
Data Index: 812299 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.4296. Min Act: -0.1700
Data Index: 945523 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.4296. Min Act: -0.1700
Data Index: 321197 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.4296. Min Act: -0.1700
Data Index: 738386 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.3984. Min Act: -0.1700
Data Index: 812310 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.4609. Min Act: -0.1700
Data Index: 1320806 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.3671. Min Act: -0.1700
Data Index: 1197843 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.3984. Min Act: -0.1700
Data Index: 37443 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.3984. Min Act: -0.1700
Data Index: 1099426 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7734. Min Range: -4.7734
Max Act: 4.3671. Min Act: -0.1700
Data Index: 1227880 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19