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

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

Neuron 4054 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0431. Min Act: -0.0002

Data Index: 985136 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0325. Min Act: -0.0002

Data Index: 550053 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0350. Min Act: -0.0002

Data Index: 520124 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0279. Min Act: -0.0002

Data Index: 83224 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0309. Min Act: -0.0002

Data Index: 816098 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0351. Min Act: -0.0002

Data Index: 484206 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0330. Min Act: -0.0003

Data Index: 903136 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0331. Min Act: -0.0002

Data Index: 113089 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1345436 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0329. Min Act: -0.0002

Data Index: 415001 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0332. Min Act: -0.0002

Data Index: 11531 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1391446 (Python Code)

Max Activating Token Index: 707

Text #12

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0330. Min Act: -0.0002

Data Index: 1307857 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0298. Min Act: -0.0002

Data Index: 976925 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0285. Min Act: -0.0002

Data Index: 144561 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0281. Min Act: -0.0002

Data Index: 873590 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1040737 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0328. Min Act: -0.0002

Data Index: 325819 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0298. Min Act: -0.0002

Data Index: 97655 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.0431. Min Range: -0.0431

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1098313 (C4 (Web Text))

Max Activating Token Index: 91