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

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

Neuron 2624 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3982. Min Range: -2.3982

Max Act: 2.3982. Min Act: -0.0000

Data Index: 523411 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 2.3982. Min Range: -2.3982

Max Act: 2.2325. Min Act: -0.0000

Data Index: 142334 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 2.3982. Min Range: -2.3982

Max Act: 1.9853. Min Act: -0.0000

Data Index: 773496 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 2.3982. Min Range: -2.3982

Max Act: 2.0866. Min Act: -0.0000

Data Index: 117387 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 2.3982. Min Range: -2.3982

Max Act: 2.0465. Min Act: -0.0000

Data Index: 998353 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 2.3982. Min Range: -2.3982

Max Act: 1.9291. Min Act: -0.0000

Data Index: 817015 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 2.3982. Min Range: -2.3982

Max Act: 1.8629. Min Act: -0.0000

Data Index: 713690 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 2.3982. Min Range: -2.3982

Max Act: 1.7177. Min Act: -0.0000

Data Index: 49845 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 2.3982. Min Range: -2.3982

Max Act: 1.7853. Min Act: -0.0000

Data Index: 245338 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 2.3982. Min Range: -2.3982

Max Act: 1.7543. Min Act: -0.0000

Data Index: 285240 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 2.3982. Min Range: -2.3982

Max Act: 1.7772. Min Act: -0.0000

Data Index: 1341602 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 2.3982. Min Range: -2.3982

Max Act: 1.7552. Min Act: -0.0000

Data Index: 117355 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 2.3982. Min Range: -2.3982

Max Act: 1.7589. Min Act: -0.0000

Data Index: 2546 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 2.3982. Min Range: -2.3982

Max Act: 1.7134. Min Act: -0.0000

Data Index: 903027 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 2.3982. Min Range: -2.3982

Max Act: 1.7039. Min Act: -0.0000

Data Index: 313786 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 2.3982. Min Range: -2.3982

Max Act: 1.7531. Min Act: -0.0000

Data Index: 302013 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 2.3982. Min Range: -2.3982

Max Act: 1.6972. Min Act: -0.0000

Data Index: 565916 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 2.3982. Min Range: -2.3982

Max Act: 1.6459. Min Act: -0.0000

Data Index: 1027093 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 2.3982. Min Range: -2.3982

Max Act: 1.5826. Min Act: -0.0000

Data Index: 270431 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 2.3982. Min Range: -2.3982

Max Act: 1.6314. Min Act: -0.0000

Data Index: 941085 (C4 (Web Text))

Max Activating Token Index: 301