Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1994 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.4628. Min Act: -0.0001
Data Index: 291541 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.3485. Min Act: -0.0001
Data Index: 824082 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.3559. Min Act: -0.0001
Data Index: 306418 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.3430. Min Act: -0.0001
Data Index: 1292566 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.3222. Min Act: -0.0001
Data Index: 680740 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.2979. Min Act: -0.0001
Data Index: 1023296 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.3293. Min Act: -0.0001
Data Index: 1281790 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.2756. Min Act: -0.0001
Data Index: 1380097 (Python Code)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.2699. Min Act: -0.0001
Data Index: 227263 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.2791. Min Act: -0.0001
Data Index: 1082525 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.2770. Min Act: -0.0001
Data Index: 921084 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.3103. Min Act: -0.0001
Data Index: 385406 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.2273. Min Act: -0.0001
Data Index: 909011 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.2676. Min Act: -0.0001
Data Index: 532151 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.2437. Min Act: -0.0001
Data Index: 356012 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.2732. Min Act: -0.0001
Data Index: 1338099 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.2503. Min Act: -0.0001
Data Index: 1150033 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.2275. Min Act: -0.0001
Data Index: 376026 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.2360. Min Act: -0.0001
Data Index: 608058 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4628. Min Range: -0.4628
Max Act: 0.2434. Min Act: -0.0001
Data Index: 110415 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19