Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4608 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.4102. Min Act: -0.0000

Data Index: 1321345 (The Pile)

Max Activating Token Index: 390

Text #1

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.1304. Min Act: -0.0000

Data Index: 521273 (The Pile)

Max Activating Token Index: 318

Text #2

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2561. Min Act: -0.0000

Data Index: 855016 (The Pile)

Max Activating Token Index: 121

Text #3

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.0856. Min Act: -0.0000

Data Index: 250830 (The Pile)

Max Activating Token Index: 703

Text #4

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.1564. Min Act: -0.0000

Data Index: 1943146 (The Pile)

Max Activating Token Index: 548

Text #5

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.1163. Min Act: -0.0000

Data Index: 317914 (The Pile)

Max Activating Token Index: 253

Text #6

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.9749. Min Act: -0.0000

Data Index: 968041 (The Pile)

Max Activating Token Index: 208

Text #7

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.2445. Min Act: -0.0000

Data Index: 687955 (The Pile)

Max Activating Token Index: 664

Text #8

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.9813. Min Act: -0.0000

Data Index: 1520742 (The Pile)

Max Activating Token Index: 788

Text #9

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.9452. Min Act: -0.0000

Data Index: 1498948 (The Pile)

Max Activating Token Index: 568

Text #10

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.0920. Min Act: -0.0001

Data Index: 1768503 (The Pile)

Max Activating Token Index: 521

Text #11

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.0956. Min Act: -0.0000

Data Index: 1561229 (The Pile)

Max Activating Token Index: 939

Text #12

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.0447. Min Act: -0.0000

Data Index: 871266 (The Pile)

Max Activating Token Index: 487

Text #13

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.0524. Min Act: -0.0000

Data Index: 194858 (The Pile)

Max Activating Token Index: 267

Text #14

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.1528. Min Act: -0.0000

Data Index: 545408 (The Pile)

Max Activating Token Index: 669

Text #15

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.7461. Min Act: -0.0000

Data Index: 376949 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.0428. Min Act: -0.0000

Data Index: 1873553 (The Pile)

Max Activating Token Index: 932

Text #17

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.9347. Min Act: -0.0000

Data Index: 1682939 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.9368. Min Act: -0.0000

Data Index: 32083 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.9224. Min Act: -0.0000

Data Index: 304233 (The Pile)

Max Activating Token Index: 273