Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3943 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.5748. Min Act: -0.0001
Data Index: 655265 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.4542. Min Act: -0.0001
Data Index: 1071053 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.2309. Min Act: -0.0001
Data Index: 618305 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.5239. Min Act: -0.0001
Data Index: 624791 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.4333. Min Act: -0.0001
Data Index: 1036432 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.2050. Min Act: -0.0001
Data Index: 746685 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3679. Min Act: -0.0001
Data Index: 441231 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3229. Min Act: -0.0001
Data Index: 518512 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3971. Min Act: -0.0001
Data Index: 953057 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3507. Min Act: -0.0001
Data Index: 1077046 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3353. Min Act: -0.0001
Data Index: 1248767 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.4819. Min Act: -0.0001
Data Index: 908025 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.2494. Min Act: -0.0001
Data Index: 88242 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.4788. Min Act: -0.0001
Data Index: 702901 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3456. Min Act: -0.0001
Data Index: 1132664 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.4277. Min Act: -0.0001
Data Index: 1029553 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.2269. Min Act: -0.0001
Data Index: 666436 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.3336. Min Act: -0.0001
Data Index: 293859 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.4849. Min Act: -0.0001
Data Index: 27858 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5748. Min Range: -1.5748
Max Act: 1.2906. Min Act: -0.0001
Data Index: 1208251 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19