Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2035 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.5614. Min Act: -0.0001
Data Index: 1351903 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.5733. Min Act: -0.0001
Data Index: 1072670 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.5499. Min Act: -0.0001
Data Index: 1101103 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.5065. Min Act: -0.0001
Data Index: 329325 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.5191. Min Act: -0.0001
Data Index: 371288 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.4710. Min Act: -0.0001
Data Index: 1084496 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.4834. Min Act: -0.0001
Data Index: 1164188 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.4957. Min Act: -0.0001
Data Index: 338759 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.4716. Min Act: -0.0001
Data Index: 1294075 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.4863. Min Act: -0.0001
Data Index: 894773 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.4447. Min Act: -0.0001
Data Index: 1023720 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.4571. Min Act: -0.0001
Data Index: 1459137 (Python Code)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.4555. Min Act: -0.0001
Data Index: 92934 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.4418. Min Act: -0.0001
Data Index: 1156733 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.4142. Min Act: -0.0001
Data Index: 328865 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.4651. Min Act: -0.0001
Data Index: 106906 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.4459. Min Act: -0.0001
Data Index: 775378 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.4124. Min Act: -0.0001
Data Index: 1164452 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.4138. Min Act: -0.0001
Data Index: 826289 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5733. Min Range: -0.5733
Max Act: 0.4245. Min Act: -0.0001
Data Index: 1495995 (Python Code)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19