Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 888 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.4397. Min Act: -0.0000

Data Index: 1279617 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.1337. Min Act: -0.0000

Data Index: 288929 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.0534. Min Act: -0.0000

Data Index: 29922 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 3.4397. Min Range: -3.4397

Max Act: 3.0779. Min Act: -0.0000

Data Index: 682455 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 3.4397. Min Range: -3.4397

Max Act: 2.7509. Min Act: -0.0000

Data Index: 548740 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 3.4397. Min Range: -3.4397

Max Act: 2.7967. Min Act: -0.0000

Data Index: 519149 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 3.4397. Min Range: -3.4397

Max Act: 2.7880. Min Act: -0.0000

Data Index: 615444 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 3.4397. Min Range: -3.4397

Max Act: 2.7170. Min Act: -0.0000

Data Index: 21543 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 3.4397. Min Range: -3.4397

Max Act: 2.6430. Min Act: -0.0000

Data Index: 970279 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 3.4397. Min Range: -3.4397

Max Act: 2.4061. Min Act: -0.0000

Data Index: 1476638 (Python Code)

Max Activating Token Index: 107

Text #10

Max Range: 3.4397. Min Range: -3.4397

Max Act: 2.3780. Min Act: -0.0000

Data Index: 983368 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 3.4397. Min Range: -3.4397

Max Act: 2.1193. Min Act: -0.0000

Data Index: 884086 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 3.4397. Min Range: -3.4397

Max Act: 2.3485. Min Act: -0.0000

Data Index: 886776 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 3.4397. Min Range: -3.4397

Max Act: 2.2080. Min Act: -0.0000

Data Index: 88654 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 3.4397. Min Range: -3.4397

Max Act: 1.9512. Min Act: -0.0000

Data Index: 959971 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 3.4397. Min Range: -3.4397

Max Act: 1.8909. Min Act: -0.0000

Data Index: 951681 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 3.4397. Min Range: -3.4397

Max Act: 1.9718. Min Act: -0.0000

Data Index: 1285975 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 3.4397. Min Range: -3.4397

Max Act: 1.9710. Min Act: -0.0000

Data Index: 803194 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 3.4397. Min Range: -3.4397

Max Act: 2.0708. Min Act: -0.0000

Data Index: 1104686 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 3.4397. Min Range: -3.4397

Max Act: 1.9204. Min Act: -0.0000

Data Index: 1028007 (C4 (Web Text))

Max Activating Token Index: 719