Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4335 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.0731. Min Range: -3.0731

Max Act: 3.0731. Min Act: -0.0000

Data Index: 700700 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 3.0731. Min Range: -3.0731

Max Act: 3.0271. Min Act: -0.0000

Data Index: 146496 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 3.0731. Min Range: -3.0731

Max Act: 3.0190. Min Act: -0.0000

Data Index: 322284 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.9878. Min Act: -0.0000

Data Index: 490057 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.9438. Min Act: -0.0000

Data Index: 556278 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.8038. Min Act: -0.0000

Data Index: 249595 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.8879. Min Act: -0.0000

Data Index: 800383 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.9395. Min Act: -0.0000

Data Index: 973961 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.5841. Min Act: -0.0000

Data Index: 1067436 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.7213. Min Act: -0.0000

Data Index: 101553 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.5402. Min Act: -0.0000

Data Index: 1308995 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.5552. Min Act: -0.0000

Data Index: 448280 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.5445. Min Act: -0.0000

Data Index: 994808 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.4125. Min Act: -0.0000

Data Index: 702341 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.4024. Min Act: -0.0000

Data Index: 138414 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.4791. Min Act: -0.0000

Data Index: 1097234 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.4368. Min Act: -0.0000

Data Index: 329816 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.4118. Min Act: -0.0000

Data Index: 1060474 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.4348. Min Act: -0.0000

Data Index: 481704 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.4017. Min Act: -0.0000

Data Index: 619358 (C4 (Web Text))

Max Activating Token Index: 339