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

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

Neuron 4064 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2647. Min Act: -0.0000

Data Index: 83818 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2634. Min Act: -0.0000

Data Index: 772226 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2591. Min Act: -0.0000

Data Index: 784372 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2452. Min Act: -0.0001

Data Index: 451229 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2421. Min Act: -0.0001

Data Index: 201031 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2472. Min Act: -0.0001

Data Index: 748534 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2279. Min Act: -0.0000

Data Index: 1099335 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2407. Min Act: -0.0000

Data Index: 780444 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2233. Min Act: -0.0001

Data Index: 126500 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2352. Min Act: -0.0001

Data Index: 136175 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2275. Min Act: -0.0001

Data Index: 968184 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2296. Min Act: -0.0001

Data Index: 698020 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2179. Min Act: -0.0001

Data Index: 757449 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2358. Min Act: -0.0000

Data Index: 611002 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2228. Min Act: -0.0000

Data Index: 536836 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2107. Min Act: -0.0001

Data Index: 256498 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2036. Min Act: -0.0001

Data Index: 544300 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1319354 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2045. Min Act: -0.0001

Data Index: 481418 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2099. Min Act: -0.0001

Data Index: 523486 (C4 (Web Text))

Max Activating Token Index: 14