Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2065 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.9583. Min Act: -0.0001
Data Index: 922593 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.9052. Min Act: -0.0001
Data Index: 39625 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.9569. Min Act: -0.0001
Data Index: 479556 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.8965. Min Act: -0.0001
Data Index: 355110 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.9201. Min Act: -0.0001
Data Index: 1181434 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.8400. Min Act: -0.0001
Data Index: 687235 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.9029. Min Act: -0.0001
Data Index: 47761 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.9031. Min Act: -0.0001
Data Index: 431783 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.8316. Min Act: -0.0001
Data Index: 1250114 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.8249. Min Act: -0.0001
Data Index: 1150290 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.8992. Min Act: -0.0001
Data Index: 1157383 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.8703. Min Act: -0.0001
Data Index: 916716 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.9383. Min Act: -0.0001
Data Index: 39856 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.8999. Min Act: -0.0001
Data Index: 848407 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.8212. Min Act: -0.0001
Data Index: 530101 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.8258. Min Act: -0.0001
Data Index: 567516 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.8483. Min Act: -0.0001
Data Index: 866177 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.8131. Min Act: -0.0001
Data Index: 753521 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.8249. Min Act: -0.0001
Data Index: 569843 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9583. Min Range: -0.9583
Max Act: 0.8434. Min Act: -0.0001
Data Index: 773735 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19