Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2592 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.5985. Min Range: -2.5985
Max Act: 2.5985. Min Act: -0.0001
Data Index: 1068920 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5985. Min Range: -2.5985
Max Act: 1.8962. Min Act: -0.0000
Data Index: 133314 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5985. Min Range: -2.5985
Max Act: 1.6858. Min Act: -0.0000
Data Index: 1197399 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5985. Min Range: -2.5985
Max Act: 1.7617. Min Act: -0.0001
Data Index: 907917 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5985. Min Range: -2.5985
Max Act: 1.7873. Min Act: -0.0001
Data Index: 288847 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5985. Min Range: -2.5985
Max Act: 1.7126. Min Act: -0.0000
Data Index: 985395 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5985. Min Range: -2.5985
Max Act: 1.6134. Min Act: -0.0000
Data Index: 24131 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5985. Min Range: -2.5985
Max Act: 1.5916. Min Act: -0.0001
Data Index: 1123824 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5985. Min Range: -2.5985
Max Act: 1.5364. Min Act: -0.0000
Data Index: 1103804 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5985. Min Range: -2.5985
Max Act: 1.3716. Min Act: -0.0001
Data Index: 951501 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5985. Min Range: -2.5985
Max Act: 1.7245. Min Act: -0.0001
Data Index: 340709 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5985. Min Range: -2.5985
Max Act: 1.6134. Min Act: -0.0001
Data Index: 1350880 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5985. Min Range: -2.5985
Max Act: 1.5408. Min Act: -0.0000
Data Index: 946182 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5985. Min Range: -2.5985
Max Act: 1.5015. Min Act: -0.0001
Data Index: 889771 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5985. Min Range: -2.5985
Max Act: 1.4992. Min Act: -0.0000
Data Index: 952902 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5985. Min Range: -2.5985
Max Act: 1.4898. Min Act: -0.0000
Data Index: 212199 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5985. Min Range: -2.5985
Max Act: 1.4801. Min Act: -0.0001
Data Index: 287602 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5985. Min Range: -2.5985
Max Act: 1.4878. Min Act: -0.0000
Data Index: 49660 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5985. Min Range: -2.5985
Max Act: 1.4115. Min Act: -0.0001
Data Index: 219345 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5985. Min Range: -2.5985
Max Act: 1.4671. Min Act: -0.0001
Data Index: 51476 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19