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

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

Neuron 2901 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2607. Min Act: -0.0001

Data Index: 418560 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2339. Min Act: -0.0001

Data Index: 344871 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2436. Min Act: -0.0001

Data Index: 1139909 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2418. Min Act: -0.0001

Data Index: 1088130 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2221. Min Act: -0.0001

Data Index: 421464 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2380. Min Act: -0.0001

Data Index: 1211189 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2282. Min Act: -0.0001

Data Index: 516109 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2400. Min Act: -0.0001

Data Index: 880055 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2323. Min Act: -0.0001

Data Index: 957303 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2306. Min Act: -0.0001

Data Index: 136117 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2378. Min Act: -0.0001

Data Index: 878481 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2281. Min Act: -0.0001

Data Index: 22499 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2267. Min Act: -0.0001

Data Index: 926782 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2182. Min Act: -0.0001

Data Index: 555544 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2197. Min Act: -0.0001

Data Index: 944430 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2307. Min Act: -0.0001

Data Index: 160392 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2324. Min Act: -0.0001

Data Index: 40229 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2395. Min Act: -0.0001

Data Index: 1096996 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2321. Min Act: -0.0001

Data Index: 813034 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.2607. Min Range: -0.2607

Max Act: 0.2241. Min Act: -0.0001

Data Index: 663193 (C4 (Web Text))

Max Activating Token Index: 52