Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 708 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.9084. Min Act: -0.0001
Data Index: 756445 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.7958. Min Act: -0.0001
Data Index: 633868 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.9374. Min Act: -0.0001
Data Index: 268797 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.8223. Min Act: -0.0001
Data Index: 190041 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.8722. Min Act: -0.0001
Data Index: 57714 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.8877. Min Act: -0.0001
Data Index: 649330 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.8469. Min Act: -0.0001
Data Index: 1405508 (Python Code)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.8294. Min Act: -0.0001
Data Index: 68944 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.8281. Min Act: -0.0001
Data Index: 416498 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.8180. Min Act: -0.0001
Data Index: 1430768 (Python Code)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.7424. Min Act: -0.0001
Data Index: 37856 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.7820. Min Act: -0.0001
Data Index: 616148 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.8080. Min Act: -0.0001
Data Index: 1035871 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.7582. Min Act: -0.0001
Data Index: 274580 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.7987. Min Act: -0.0001
Data Index: 1088643 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.7473. Min Act: -0.0001
Data Index: 1109314 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.7424. Min Act: -0.0001
Data Index: 97213 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.6430. Min Act: -0.0001
Data Index: 1224442 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.7007. Min Act: -0.0001
Data Index: 1327031 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9374. Min Range: -0.9374
Max Act: 0.6583. Min Act: -0.0001
Data Index: 1027172 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19