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

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

Neuron 3 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: 0.6212. Min Range: -0.6212

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1055621 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5148. Min Act: -0.0001

Data Index: 413109 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5093. Min Act: -0.0001

Data Index: 1375250 (Python Code)

Max Activating Token Index: 253

Text #3

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5118. Min Act: -0.0000

Data Index: 220049 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4935. Min Act: -0.0001

Data Index: 1618455 (Python Code)

Max Activating Token Index: 216

Text #5

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5093. Min Act: -0.0001

Data Index: 1454368 (Python Code)

Max Activating Token Index: 1019

Text #6

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4690. Min Act: -0.0001

Data Index: 607023 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5056. Min Act: -0.0001

Data Index: 1644721 (Python Code)

Max Activating Token Index: 565

Text #8

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4568. Min Act: -0.0001

Data Index: 1422928 (Python Code)

Max Activating Token Index: 539

Text #9

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4359. Min Act: -0.0001

Data Index: 1502788 (Python Code)

Max Activating Token Index: 741

Text #10

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4476. Min Act: -0.0001

Data Index: 1405557 (Python Code)

Max Activating Token Index: 952

Text #11

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4315. Min Act: -0.0001

Data Index: 661992 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4386. Min Act: -0.0001

Data Index: 1406244 (Python Code)

Max Activating Token Index: 509

Text #13

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4484. Min Act: -0.0001

Data Index: 1522502 (Python Code)

Max Activating Token Index: 900

Text #14

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4486. Min Act: -0.0001

Data Index: 175842 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1101099 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1321427 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4150. Min Act: -0.0001

Data Index: 1431063 (Python Code)

Max Activating Token Index: 735

Text #18

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4604. Min Act: -0.0001

Data Index: 1370588 (Python Code)

Max Activating Token Index: 685

Text #19

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4312. Min Act: -0.0001

Data Index: 1427020 (Python Code)

Max Activating Token Index: 779