Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3763 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0003

Data Index: 863839 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0003

Data Index: 694724 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0327. Min Act: -0.0003

Data Index: 432959 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0003

Data Index: 457921 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0326. Min Act: -0.0003

Data Index: 1063955 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0323. Min Act: -0.0003

Data Index: 500470 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0322. Min Act: -0.0003

Data Index: 110975 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0321. Min Act: -0.0003

Data Index: 362651 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0321. Min Act: -0.0003

Data Index: 704609 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0323. Min Act: -0.0002

Data Index: 269947 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0311. Min Act: -0.0003

Data Index: 148781 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0315. Min Act: -0.0002

Data Index: 419359 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0320. Min Act: -0.0003

Data Index: 515910 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0314. Min Act: -0.0003

Data Index: 366920 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0313. Min Act: -0.0003

Data Index: 212271 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0310. Min Act: -0.0003

Data Index: 920130 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0309. Min Act: -0.0003

Data Index: 27767 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1275417 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0315. Min Act: -0.0003

Data Index: 649577 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0308. Min Act: -0.0003

Data Index: 619390 (C4 (Web Text))

Max Activating Token Index: 40