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

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

Neuron 3374 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.3121. Min Act: -0.0001

Data Index: 1237402 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2669. Min Act: -0.0001

Data Index: 1202437 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2939. Min Act: -0.0001

Data Index: 661615 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.3006. Min Act: -0.0001

Data Index: 780172 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2841. Min Act: -0.0001

Data Index: 225243 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2755. Min Act: -0.0001

Data Index: 441671 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2762. Min Act: -0.0001

Data Index: 1003153 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2497. Min Act: -0.0001

Data Index: 1245011 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2422. Min Act: -0.0001

Data Index: 1020874 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2478. Min Act: -0.0001

Data Index: 667565 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2439. Min Act: -0.0001

Data Index: 299983 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2407. Min Act: -0.0001

Data Index: 545235 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2452. Min Act: -0.0001

Data Index: 484862 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2454. Min Act: -0.0001

Data Index: 367243 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2285. Min Act: -0.0001

Data Index: 207037 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2300. Min Act: -0.0001

Data Index: 203855 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2284. Min Act: -0.0001

Data Index: 585421 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2137. Min Act: -0.0001

Data Index: 89286 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2280. Min Act: -0.0001

Data Index: 79664 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2266. Min Act: -0.0001

Data Index: 1011739 (C4 (Web Text))

Max Activating Token Index: 615