Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4206 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.3786. Min Act: -0.0001
Data Index: 904702 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.3550. Min Act: -0.0001
Data Index: 1292436 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.3431. Min Act: -0.0001
Data Index: 303835 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.3402. Min Act: -0.0001
Data Index: 53364 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.3433. Min Act: -0.0001
Data Index: 968973 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.3396. Min Act: -0.0001
Data Index: 948454 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.3187. Min Act: -0.0001
Data Index: 691760 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.3300. Min Act: -0.0001
Data Index: 809774 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.3133. Min Act: -0.0001
Data Index: 444730 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.3075. Min Act: -0.0001
Data Index: 221107 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.2984. Min Act: -0.0001
Data Index: 1243927 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.2933. Min Act: -0.0001
Data Index: 1106739 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.2965. Min Act: -0.0001
Data Index: 1127208 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.2694. Min Act: -0.0001
Data Index: 1100077 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.2975. Min Act: -0.0001
Data Index: 504285 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.2971. Min Act: -0.0001
Data Index: 167318 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.2925. Min Act: -0.0001
Data Index: 640439 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.2816. Min Act: -0.0001
Data Index: 1148702 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.2886. Min Act: -0.0001
Data Index: 743194 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3786. Min Range: -0.3786
Max Act: 0.3005. Min Act: -0.0001
Data Index: 136064 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19