Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4052 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.9349. Min Act: -0.0001
Data Index: 551532 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.9258. Min Act: -0.0001
Data Index: 1267873 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.8453. Min Act: -0.0001
Data Index: 274594 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.7817. Min Act: -0.0001
Data Index: 1016337 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.8098. Min Act: -0.0001
Data Index: 482483 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.8047. Min Act: -0.0001
Data Index: 551010 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.7548. Min Act: -0.0001
Data Index: 774599 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.7500. Min Act: -0.0001
Data Index: 163217 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.7212. Min Act: -0.0001
Data Index: 1084824 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.7403. Min Act: -0.0001
Data Index: 573663 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.7121. Min Act: -0.0001
Data Index: 90467 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.7595. Min Act: -0.0001
Data Index: 260623 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.7031. Min Act: -0.0001
Data Index: 1226706 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.7480. Min Act: -0.0001
Data Index: 1108604 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.7482. Min Act: -0.0001
Data Index: 119757 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.7509. Min Act: -0.0001
Data Index: 619818 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.6857. Min Act: -0.0001
Data Index: 192534 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.7675. Min Act: -0.0001
Data Index: 894786 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.6725. Min Act: -0.0001
Data Index: 1305211 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9349. Min Range: -0.9349
Max Act: 0.6885. Min Act: -0.0001
Data Index: 892958 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19