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

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

Neuron 3219 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.4961. Min Act: -0.0000

Data Index: 718611 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.4547. Min Act: -0.0001

Data Index: 292242 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3960. Min Act: -0.0001

Data Index: 472472 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3575. Min Act: -0.0000

Data Index: 719299 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3704. Min Act: -0.0000

Data Index: 742633 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3453. Min Act: -0.0001

Data Index: 49349 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3401. Min Act: -0.0000

Data Index: 1031611 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3348. Min Act: -0.0000

Data Index: 821612 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3330. Min Act: -0.0001

Data Index: 551162 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3200. Min Act: -0.0001

Data Index: 1228292 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3320. Min Act: -0.0000

Data Index: 914415 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3245. Min Act: -0.0000

Data Index: 46070 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3140. Min Act: -0.0001

Data Index: 250398 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3005. Min Act: -0.0000

Data Index: 1346045 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.2417. Min Act: -0.0001

Data Index: 1504365 (Python Code)

Max Activating Token Index: 855

Text #15

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.2439. Min Act: -0.0000

Data Index: 897883 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.2379. Min Act: -0.0001

Data Index: 1482550 (Python Code)

Max Activating Token Index: 839

Text #17

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.2284. Min Act: -0.0001

Data Index: 1635261 (Python Code)

Max Activating Token Index: 914

Text #18

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.2428. Min Act: -0.0001

Data Index: 1320171 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.2161. Min Act: -0.0001

Data Index: 1458142 (Python Code)

Max Activating Token Index: 726