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

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

Neuron 226 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: 0.4359. Min Range: -0.4359

Max Act: 0.4278. Min Act: -0.0001

Data Index: 420190 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.4359. Min Act: -0.0001

Data Index: 1268117 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.4170. Min Act: -0.0001

Data Index: 1172708 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3521. Min Act: -0.0001

Data Index: 512081 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3450. Min Act: -0.0001

Data Index: 1132345 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3577. Min Act: -0.0001

Data Index: 681317 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3586. Min Act: -0.0001

Data Index: 59250 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3354. Min Act: -0.0001

Data Index: 93086 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3636. Min Act: -0.0001

Data Index: 539986 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3244. Min Act: -0.0001

Data Index: 215694 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3044. Min Act: -0.0001

Data Index: 373921 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3304. Min Act: -0.0001

Data Index: 1377958 (Python Code)

Max Activating Token Index: 800

Text #12

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.2917. Min Act: -0.0001

Data Index: 987277 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3230. Min Act: -0.0001

Data Index: 277379 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3217. Min Act: -0.0001

Data Index: 1003720 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3015. Min Act: -0.0001

Data Index: 574814 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3101. Min Act: -0.0001

Data Index: 1611985 (Python Code)

Max Activating Token Index: 8

Text #17

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3195. Min Act: -0.0001

Data Index: 641083 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3013. Min Act: -0.0001

Data Index: 645131 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.4359. Min Range: -0.4359

Max Act: 0.3231. Min Act: -0.0001

Data Index: 1515835 (Python Code)

Max Activating Token Index: 694