Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1954 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1414. Min Act: -0.0002

Data Index: 445085 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1501. Min Act: -0.0002

Data Index: 979830 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1425. Min Act: -0.0002

Data Index: 195496 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1378. Min Act: -0.0002

Data Index: 1345364 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1392. Min Act: -0.0002

Data Index: 266554 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1378. Min Act: -0.0001

Data Index: 80933 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1378. Min Act: -0.0001

Data Index: 33803 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1470. Min Act: -0.0002

Data Index: 75958 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1312. Min Act: -0.0002

Data Index: 821226 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1379. Min Act: -0.0002

Data Index: 607182 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1375. Min Act: -0.0002

Data Index: 641211 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1272. Min Act: -0.0002

Data Index: 585516 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1322. Min Act: -0.0002

Data Index: 75304 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1318. Min Act: -0.0002

Data Index: 933551 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1233. Min Act: -0.0001

Data Index: 134052 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1293. Min Act: -0.0001

Data Index: 887326 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1329. Min Act: -0.0002

Data Index: 561149 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1232. Min Act: -0.0002

Data Index: 556592 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1230. Min Act: -0.0002

Data Index: 74508 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1233. Min Act: -0.0002

Data Index: 1049161 (C4 (Web Text))

Max Activating Token Index: 21