Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2380 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.2570. Min Act: -0.0004
Data Index: 563014 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.2027. Min Act: -0.0004
Data Index: 1329454 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.2262. Min Act: -0.0004
Data Index: 505988 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.2065. Min Act: -0.0004
Data Index: 136298 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.2203. Min Act: -0.0004
Data Index: 326126 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.2396. Min Act: -0.0004
Data Index: 68896 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.2137. Min Act: -0.0004
Data Index: 584740 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.1907. Min Act: -0.0004
Data Index: 585780 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.1959. Min Act: -0.0004
Data Index: 922076 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.1998. Min Act: -0.0004
Data Index: 502740 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.1941. Min Act: -0.0004
Data Index: 24699 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.1936. Min Act: -0.0004
Data Index: 69412 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.2180. Min Act: -0.0004
Data Index: 227424 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.1702. Min Act: -0.0004
Data Index: 925533 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.1872. Min Act: -0.0004
Data Index: 482986 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.1861. Min Act: -0.0004
Data Index: 76418 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.1892. Min Act: -0.0004
Data Index: 605965 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.1877. Min Act: -0.0004
Data Index: 1341810 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.1867. Min Act: -0.0004
Data Index: 857148 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2570. Min Range: -0.2570
Max Act: 0.2556. Min Act: -0.0004
Data Index: 946067 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19