Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5637 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6892. Min Act: -0.0000

Data Index: 889410 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6964. Min Act: -0.0000

Data Index: 599934 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6512. Min Act: -0.0000

Data Index: 492630 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6932. Min Act: -0.0000

Data Index: 193977 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6323. Min Act: -0.0000

Data Index: 660216 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6269. Min Act: -0.0000

Data Index: 324884 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6084. Min Act: -0.0000

Data Index: 414855 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1001923 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6690. Min Act: -0.0000

Data Index: 878015 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6300. Min Act: -0.0000

Data Index: 585785 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6693. Min Act: -0.0000

Data Index: 289165 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6235. Min Act: -0.0000

Data Index: 808217 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6673. Min Act: -0.0000

Data Index: 647611 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6478. Min Act: -0.0000

Data Index: 24816 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1330047 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1124144 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6334. Min Act: -0.0000

Data Index: 1157992 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6481. Min Act: -0.0000

Data Index: 235859 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6206. Min Act: -0.0000

Data Index: 115748 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6309. Min Act: -0.0000

Data Index: 767556 (C4 (Web Text))

Max Activating Token Index: 616