Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4467 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.2021. Min Range: -1.2021
Max Act: 1.2021. Min Act: -0.0001
Data Index: 1172944 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2021. Min Range: -1.2021
Max Act: 1.2013. Min Act: -0.0001
Data Index: 117094 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2021. Min Range: -1.2021
Max Act: 1.0898. Min Act: -0.0001
Data Index: 1079502 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2021. Min Range: -1.2021
Max Act: 1.0203. Min Act: -0.0001
Data Index: 390474 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2021. Min Range: -1.2021
Max Act: 1.0469. Min Act: -0.0001
Data Index: 411041 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2021. Min Range: -1.2021
Max Act: 1.0334. Min Act: -0.0001
Data Index: 641179 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2021. Min Range: -1.2021
Max Act: 0.9415. Min Act: -0.0001
Data Index: 308827 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2021. Min Range: -1.2021
Max Act: 0.9606. Min Act: -0.0001
Data Index: 260212 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2021. Min Range: -1.2021
Max Act: 0.8866. Min Act: -0.0001
Data Index: 46767 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2021. Min Range: -1.2021
Max Act: 0.9610. Min Act: -0.0001
Data Index: 397406 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2021. Min Range: -1.2021
Max Act: 1.0659. Min Act: -0.0001
Data Index: 381372 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2021. Min Range: -1.2021
Max Act: 0.9183. Min Act: -0.0001
Data Index: 943161 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2021. Min Range: -1.2021
Max Act: 0.9780. Min Act: -0.0001
Data Index: 751464 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2021. Min Range: -1.2021
Max Act: 0.8788. Min Act: -0.0001
Data Index: 1077088 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2021. Min Range: -1.2021
Max Act: 0.8547. Min Act: -0.0001
Data Index: 906787 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2021. Min Range: -1.2021
Max Act: 0.9048. Min Act: -0.0001
Data Index: 60998 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2021. Min Range: -1.2021
Max Act: 0.8493. Min Act: -0.0000
Data Index: 1017391 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2021. Min Range: -1.2021
Max Act: 0.8042. Min Act: -0.0001
Data Index: 890177 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2021. Min Range: -1.2021
Max Act: 0.9150. Min Act: -0.0001
Data Index: 180118 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2021. Min Range: -1.2021
Max Act: 0.8830. Min Act: -0.0001
Data Index: 1337058 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19