Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1978 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.5421. Min Act: -0.0001
Data Index: 946172 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.4859. Min Act: -0.0001
Data Index: 849314 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.4230. Min Act: -0.0001
Data Index: 415135 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.4184. Min Act: -0.0001
Data Index: 233897 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.4212. Min Act: -0.0001
Data Index: 1053863 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.3932. Min Act: -0.0001
Data Index: 1300268 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.3963. Min Act: -0.0001
Data Index: 1136190 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.4212. Min Act: -0.0001
Data Index: 1629758 (Python Code)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.4617. Min Act: -0.0001
Data Index: 359280 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.3413. Min Act: -0.0001
Data Index: 582811 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.3896. Min Act: -0.0001
Data Index: 220331 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.4069. Min Act: -0.0001
Data Index: 183694 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.3762. Min Act: -0.0001
Data Index: 931059 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.3930. Min Act: -0.0001
Data Index: 1162336 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.3832. Min Act: -0.0001
Data Index: 1211276 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.3720. Min Act: -0.0001
Data Index: 877121 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.3582. Min Act: -0.0001
Data Index: 373487 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.3692. Min Act: -0.0001
Data Index: 1483334 (Python Code)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.3675. Min Act: -0.0001
Data Index: 1104062 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5421. Min Range: -0.5421
Max Act: 0.3438. Min Act: -0.0001
Data Index: 633799 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19