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

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

Neuron 2372 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2882. Min Act: -0.0001

Data Index: 1022039 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2765. Min Act: -0.0001

Data Index: 671517 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2501. Min Act: -0.0001

Data Index: 866826 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2512. Min Act: -0.0000

Data Index: 904115 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2349. Min Act: -0.0001

Data Index: 572844 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1182524 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2297. Min Act: -0.0000

Data Index: 623361 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2332. Min Act: -0.0000

Data Index: 894840 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1121751 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2298. Min Act: -0.0000

Data Index: 1305296 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2272. Min Act: -0.0001

Data Index: 878949 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2196. Min Act: -0.0001

Data Index: 377720 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1018665 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2417. Min Act: -0.0001

Data Index: 178606 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2264. Min Act: -0.0000

Data Index: 575923 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2282. Min Act: -0.0001

Data Index: 720733 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2078. Min Act: -0.0000

Data Index: 279677 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1942. Min Act: -0.0000

Data Index: 636351 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2083. Min Act: -0.0000

Data Index: 51619 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2034. Min Act: -0.0000

Data Index: 851017 (C4 (Web Text))

Max Activating Token Index: 872