Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1806 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.2314. Min Act: -0.0001
Data Index: 634648 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.2294. Min Act: -0.0001
Data Index: 752898 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.2087. Min Act: -0.0001
Data Index: 658407 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.2038. Min Act: -0.0001
Data Index: 362307 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.1958. Min Act: -0.0001
Data Index: 408079 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.1985. Min Act: -0.0001
Data Index: 955957 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.2058. Min Act: -0.0001
Data Index: 341728 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.1973. Min Act: -0.0001
Data Index: 736833 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.2022. Min Act: -0.0001
Data Index: 1178161 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.2096. Min Act: -0.0001
Data Index: 36747 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.1921. Min Act: -0.0001
Data Index: 65697 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.1953. Min Act: -0.0001
Data Index: 312027 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.1948. Min Act: -0.0001
Data Index: 106397 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.1812. Min Act: -0.0001
Data Index: 1329681 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.2020. Min Act: -0.0001
Data Index: 215026 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.1877. Min Act: -0.0001
Data Index: 493281 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.1799. Min Act: -0.0001
Data Index: 1032536 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.1665. Min Act: -0.0001
Data Index: 580719 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.1978. Min Act: -0.0001
Data Index: 1085873 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2314. Min Range: -0.2314
Max Act: 0.1840. Min Act: -0.0001
Data Index: 8369 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19