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

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

Neuron 3767 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3866. Min Act: -0.0000

Data Index: 547916 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3572. Min Act: -0.0000

Data Index: 906099 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2907. Min Act: -0.0001

Data Index: 389705 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2956. Min Act: -0.0000

Data Index: 1235733 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1278621 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2492. Min Act: -0.0001

Data Index: 1058650 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2554. Min Act: -0.0000

Data Index: 105801 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2445. Min Act: -0.0000

Data Index: 803786 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2335. Min Act: -0.0000

Data Index: 1128469 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1119932 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2253. Min Act: -0.0001

Data Index: 255406 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2366. Min Act: -0.0000

Data Index: 769294 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2177. Min Act: -0.0000

Data Index: 893597 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1125758 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2243. Min Act: -0.0001

Data Index: 287657 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2295. Min Act: -0.0000

Data Index: 911433 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1288573 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2274. Min Act: -0.0000

Data Index: 585561 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1045229 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2184. Min Act: -0.0001

Data Index: 653069 (C4 (Web Text))

Max Activating Token Index: 891