Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 358 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.7178. Min Act: -0.0001
Data Index: 36554 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.7402. Min Act: -0.0001
Data Index: 328695 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.4093. Min Act: -0.0001
Data Index: 55219 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.3577. Min Act: -0.0001
Data Index: 895981 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.3745. Min Act: -0.0001
Data Index: 33286 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.2732. Min Act: -0.0001
Data Index: 610448 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.4007. Min Act: -0.0001
Data Index: 105221 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.3185. Min Act: -0.0001
Data Index: 352057 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.3157. Min Act: -0.0001
Data Index: 392658 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.4285. Min Act: -0.0001
Data Index: 1208731 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.2925. Min Act: -0.0001
Data Index: 1214809 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.1978. Min Act: -0.0001
Data Index: 438909 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.2682. Min Act: -0.0001
Data Index: 370266 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.1624. Min Act: -0.0001
Data Index: 551714 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.1112. Min Act: -0.0001
Data Index: 1000562 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.1833. Min Act: -0.0001
Data Index: 321598 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.1707. Min Act: -0.0001
Data Index: 272424 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.1068. Min Act: -0.0001
Data Index: 1650187 (Python Code)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.1678. Min Act: -0.0001
Data Index: 905122 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7402. Min Range: -1.7402
Max Act: 1.1019. Min Act: -0.0001
Data Index: 39992 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19