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

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

Neuron 2967 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3784. Min Act: -0.0000

Data Index: 1141392 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.3370. Min Act: -0.0000

Data Index: 1289739 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2796. Min Act: -0.0000

Data Index: 717953 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2549. Min Act: -0.0000

Data Index: 994644 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1113960 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2370. Min Act: -0.0000

Data Index: 234338 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2471. Min Act: -0.0000

Data Index: 161458 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2437. Min Act: -0.0000

Data Index: 1146024 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2394. Min Act: -0.0000

Data Index: 944902 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2356. Min Act: -0.0000

Data Index: 527909 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2201. Min Act: -0.0000

Data Index: 1091082 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2271. Min Act: -0.0000

Data Index: 741465 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2242. Min Act: -0.0000

Data Index: 917668 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2311. Min Act: -0.0000

Data Index: 848452 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2243. Min Act: -0.0000

Data Index: 1196299 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2309. Min Act: -0.0000

Data Index: 86286 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1092016 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2362. Min Act: -0.0000

Data Index: 722012 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2123. Min Act: -0.0000

Data Index: 291449 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.3784. Min Range: -0.3784

Max Act: 0.2355. Min Act: -0.0000

Data Index: 609113 (C4 (Web Text))

Max Activating Token Index: 437