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

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

Neuron 2072 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0886. Min Range: -3.0886

Max Act: 3.0886. Min Act: -0.0000

Data Index: 950127 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.3178. Min Act: -0.0000

Data Index: 1077744 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.1487. Min Act: -0.0000

Data Index: 609438 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.0134. Min Act: -0.0000

Data Index: 1042274 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 3.0886. Min Range: -3.0886

Max Act: 1.9006. Min Act: -0.0000

Data Index: 1001573 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 3.0886. Min Range: -3.0886

Max Act: 1.8618. Min Act: -0.0000

Data Index: 770459 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 3.0886. Min Range: -3.0886

Max Act: 1.8406. Min Act: -0.0000

Data Index: 63357 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 3.0886. Min Range: -3.0886

Max Act: 1.8472. Min Act: -0.0000

Data Index: 1302035 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 3.0886. Min Range: -3.0886

Max Act: 1.9233. Min Act: -0.0000

Data Index: 262151 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 3.0886. Min Range: -3.0886

Max Act: 1.8152. Min Act: -0.0000

Data Index: 435148 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 3.0886. Min Range: -3.0886

Max Act: 1.7617. Min Act: -0.0000

Data Index: 343005 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 3.0886. Min Range: -3.0886

Max Act: 1.6548. Min Act: 0.0000

Data Index: 316933 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 3.0886. Min Range: -3.0886

Max Act: 1.6941. Min Act: -0.0000

Data Index: 961682 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 3.0886. Min Range: -3.0886

Max Act: 1.6796. Min Act: -0.0000

Data Index: 739188 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 3.0886. Min Range: -3.0886

Max Act: 1.6729. Min Act: -0.0000

Data Index: 735156 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 3.0886. Min Range: -3.0886

Max Act: 1.5579. Min Act: -0.0000

Data Index: 719438 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 3.0886. Min Range: -3.0886

Max Act: 1.6444. Min Act: -0.0000

Data Index: 495454 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 3.0886. Min Range: -3.0886

Max Act: 1.6320. Min Act: -0.0000

Data Index: 974010 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 3.0886. Min Range: -3.0886

Max Act: 1.5402. Min Act: -0.0000

Data Index: 368480 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 3.0886. Min Range: -3.0886

Max Act: 1.6229. Min Act: -0.0000

Data Index: 854884 (C4 (Web Text))

Max Activating Token Index: 295