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

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

Neuron 1450 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.6724. Min Act: -0.0001

Data Index: 206309 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.3898. Min Act: -0.0001

Data Index: 74295 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.3152. Min Act: -0.0001

Data Index: 985910 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.3920. Min Act: -0.0001

Data Index: 156004 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.2059. Min Act: -0.0001

Data Index: 381251 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.3468. Min Act: -0.0001

Data Index: 1308035 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.2817. Min Act: -0.0001

Data Index: 444516 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.2355. Min Act: -0.0001

Data Index: 47166 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.3108. Min Act: -0.0001

Data Index: 792521 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.2691. Min Act: -0.0001

Data Index: 660074 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.1515. Min Act: -0.0001

Data Index: 243834 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.2796. Min Act: -0.0001

Data Index: 532608 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.2686. Min Act: -0.0001

Data Index: 19582 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.1934. Min Act: -0.0001

Data Index: 43956 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.2130. Min Act: -0.0001

Data Index: 92428 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.1413. Min Act: -0.0001

Data Index: 448533 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.1600. Min Act: -0.0001

Data Index: 1211639 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.1833. Min Act: -0.0001

Data Index: 152056 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.2301. Min Act: -0.0001

Data Index: 680675 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 1.6724. Min Range: -1.6724

Max Act: 1.2210. Min Act: -0.0001

Data Index: 362781 (C4 (Web Text))

Max Activating Token Index: 627