Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2019 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.4918. Min Range: -2.4918
Max Act: 2.4918. Min Act: -0.0001
Data Index: 636845 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4918. Min Range: -2.4918
Max Act: 2.4588. Min Act: -0.0001
Data Index: 513178 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4918. Min Range: -2.4918
Max Act: 2.2631. Min Act: -0.0001
Data Index: 365078 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4918. Min Range: -2.4918
Max Act: 2.3787. Min Act: -0.0001
Data Index: 152241 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4918. Min Range: -2.4918
Max Act: 2.4622. Min Act: -0.0001
Data Index: 1246106 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4918. Min Range: -2.4918
Max Act: 2.2163. Min Act: -0.0001
Data Index: 478907 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4918. Min Range: -2.4918
Max Act: 2.3343. Min Act: -0.0001
Data Index: 151822 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4918. Min Range: -2.4918
Max Act: 2.3059. Min Act: -0.0001
Data Index: 1096553 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4918. Min Range: -2.4918
Max Act: 2.1423. Min Act: -0.0001
Data Index: 490750 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4918. Min Range: -2.4918
Max Act: 2.1051. Min Act: -0.0001
Data Index: 730815 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4918. Min Range: -2.4918
Max Act: 2.1859. Min Act: -0.0001
Data Index: 751824 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4918. Min Range: -2.4918
Max Act: 2.1724. Min Act: -0.0001
Data Index: 930111 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4918. Min Range: -2.4918
Max Act: 1.8990. Min Act: -0.0001
Data Index: 1043306 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4918. Min Range: -2.4918
Max Act: 2.2582. Min Act: -0.0001
Data Index: 172746 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4918. Min Range: -2.4918
Max Act: 2.0285. Min Act: -0.0001
Data Index: 293945 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4918. Min Range: -2.4918
Max Act: 2.1074. Min Act: -0.0001
Data Index: 170258 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4918. Min Range: -2.4918
Max Act: 2.0735. Min Act: -0.0001
Data Index: 171532 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4918. Min Range: -2.4918
Max Act: 1.9477. Min Act: -0.0001
Data Index: 152273 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4918. Min Range: -2.4918
Max Act: 1.9834. Min Act: -0.0001
Data Index: 65522 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4918. Min Range: -2.4918
Max Act: 1.9994. Min Act: -0.0001
Data Index: 681138 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19