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

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

Neuron 1570 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1366. Min Range: -2.1366

Max Act: 2.1366. Min Act: -0.0000

Data Index: 688133 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 2.1366. Min Range: -2.1366

Max Act: 2.0794. Min Act: -0.0000

Data Index: 1109511 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 2.1366. Min Range: -2.1366

Max Act: 1.6747. Min Act: -0.0000

Data Index: 1329722 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 2.1366. Min Range: -2.1366

Max Act: 1.4457. Min Act: -0.0000

Data Index: 18953 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 2.1366. Min Range: -2.1366

Max Act: 1.4724. Min Act: -0.0000

Data Index: 1205424 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 2.1366. Min Range: -2.1366

Max Act: 1.4969. Min Act: -0.0000

Data Index: 1232116 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 2.1366. Min Range: -2.1366

Max Act: 1.2898. Min Act: -0.0000

Data Index: 193399 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 2.1366. Min Range: -2.1366

Max Act: 1.3901. Min Act: -0.0000

Data Index: 322609 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 2.1366. Min Range: -2.1366

Max Act: 1.3930. Min Act: -0.0000

Data Index: 1287055 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 2.1366. Min Range: -2.1366

Max Act: 1.4650. Min Act: -0.0000

Data Index: 992620 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 2.1366. Min Range: -2.1366

Max Act: 1.3297. Min Act: -0.0000

Data Index: 788592 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 2.1366. Min Range: -2.1366

Max Act: 1.2744. Min Act: -0.0000

Data Index: 1545823 (Python Code)

Max Activating Token Index: 721

Text #12

Max Range: 2.1366. Min Range: -2.1366

Max Act: 1.4178. Min Act: -0.0000

Data Index: 491725 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 2.1366. Min Range: -2.1366

Max Act: 1.3208. Min Act: -0.0000

Data Index: 857135 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 2.1366. Min Range: -2.1366

Max Act: 1.2398. Min Act: -0.0000

Data Index: 315972 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 2.1366. Min Range: -2.1366

Max Act: 1.2553. Min Act: -0.0000

Data Index: 81219 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 2.1366. Min Range: -2.1366

Max Act: 1.3167. Min Act: -0.0000

Data Index: 1199214 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 2.1366. Min Range: -2.1366

Max Act: 1.2438. Min Act: -0.0000

Data Index: 43695 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 2.1366. Min Range: -2.1366

Max Act: 1.1961. Min Act: -0.0000

Data Index: 598164 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 2.1366. Min Range: -2.1366

Max Act: 1.2579. Min Act: -0.0000

Data Index: 1045747 (C4 (Web Text))

Max Activating Token Index: 204