Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2838 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0003

Data Index: 944950 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0391. Min Act: -0.0003

Data Index: 1005044 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1055727 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1232928 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0334. Min Act: -0.0003

Data Index: 530857 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0373. Min Act: -0.0003

Data Index: 242705 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1145393 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0260. Min Act: -0.0003

Data Index: 82539 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0363. Min Act: -0.0003

Data Index: 743081 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0321. Min Act: -0.0003

Data Index: 945563 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0300. Min Act: -0.0003

Data Index: 475912 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0315. Min Act: -0.0003

Data Index: 857431 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1117952 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0325. Min Act: -0.0003

Data Index: 593558 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0279. Min Act: -0.0003

Data Index: 300614 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0342. Min Act: -0.0003

Data Index: 945232 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0288. Min Act: -0.0003

Data Index: 35313 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0283. Min Act: -0.0003

Data Index: 1056449 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0283. Min Act: -0.0003

Data Index: 957069 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1168116 (C4 (Web Text))

Max Activating Token Index: 30