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

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

Neuron 1305 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: 0.3091. Min Range: -0.3091

Max Act: 0.3091. Min Act: -0.0000

Data Index: 584161 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.3065. Min Act: -0.0000

Data Index: 732194 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2765. Min Act: -0.0000

Data Index: 1298469 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2924. Min Act: -0.0000

Data Index: 435592 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2663. Min Act: -0.0000

Data Index: 424019 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2668. Min Act: -0.0000

Data Index: 868436 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2471. Min Act: -0.0000

Data Index: 721700 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2384. Min Act: -0.0000

Data Index: 280036 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2426. Min Act: -0.0000

Data Index: 291343 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1273927 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1322776 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2495. Min Act: -0.0000

Data Index: 1077891 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2303. Min Act: -0.0000

Data Index: 54348 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2454. Min Act: -0.0000

Data Index: 484519 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2381. Min Act: -0.0000

Data Index: 589948 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1339460 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2276. Min Act: -0.0000

Data Index: 802310 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2515. Min Act: -0.0000

Data Index: 829812 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2165. Min Act: -0.0000

Data Index: 650490 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.3091. Min Range: -0.3091

Max Act: 0.2159. Min Act: -0.0000

Data Index: 814429 (C4 (Web Text))

Max Activating Token Index: 316