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

Dataset: The Pile

Neuron 3198 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1176. Min Range: -1.1176

Max Act: 1.1176. Min Act: -0.0000

Data Index: 1802736 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 1.1176. Min Range: -1.1176

Max Act: 1.0575. Min Act: -0.0000

Data Index: 124637 (The Pile)

Max Activating Token Index: 869

Text #2

Max Range: 1.1176. Min Range: -1.1176

Max Act: 1.0830. Min Act: -0.0000

Data Index: 32571 (The Pile)

Max Activating Token Index: 382

Text #3

Max Range: 1.1176. Min Range: -1.1176

Max Act: 1.0459. Min Act: -0.0000

Data Index: 1390007 (The Pile)

Max Activating Token Index: 510

Text #4

Max Range: 1.1176. Min Range: -1.1176

Max Act: 1.0221. Min Act: -0.0000

Data Index: 1182219 (The Pile)

Max Activating Token Index: 384

Text #5

Max Range: 1.1176. Min Range: -1.1176

Max Act: 0.9718. Min Act: -0.0000

Data Index: 1760680 (The Pile)

Max Activating Token Index: 483

Text #6

Max Range: 1.1176. Min Range: -1.1176

Max Act: 0.9429. Min Act: -0.0000

Data Index: 401924 (The Pile)

Max Activating Token Index: 274

Text #7

Max Range: 1.1176. Min Range: -1.1176

Max Act: 0.9405. Min Act: -0.0000

Data Index: 574886 (The Pile)

Max Activating Token Index: 195

Text #8

Max Range: 1.1176. Min Range: -1.1176

Max Act: 1.0489. Min Act: -0.0000

Data Index: 1299182 (The Pile)

Max Activating Token Index: 767

Text #9

Max Range: 1.1176. Min Range: -1.1176

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1336856 (The Pile)

Max Activating Token Index: 194

Text #10

Max Range: 1.1176. Min Range: -1.1176

Max Act: 0.8669. Min Act: -0.0000

Data Index: 1291324 (The Pile)

Max Activating Token Index: 879

Text #11

Max Range: 1.1176. Min Range: -1.1176

Max Act: 0.9478. Min Act: -0.0000

Data Index: 773651 (The Pile)

Max Activating Token Index: 901

Text #12

Max Range: 1.1176. Min Range: -1.1176

Max Act: 0.8252. Min Act: -0.0000

Data Index: 1454942 (The Pile)

Max Activating Token Index: 900

Text #13

Max Range: 1.1176. Min Range: -1.1176

Max Act: 0.8033. Min Act: -0.0000

Data Index: 476020 (The Pile)

Max Activating Token Index: 64

Text #14

Max Range: 1.1176. Min Range: -1.1176

Max Act: 0.8997. Min Act: -0.0000

Data Index: 595162 (The Pile)

Max Activating Token Index: 911

Text #15

Max Range: 1.1176. Min Range: -1.1176

Max Act: 0.7954. Min Act: -0.0000

Data Index: 15053 (The Pile)

Max Activating Token Index: 152

Text #16

Max Range: 1.1176. Min Range: -1.1176

Max Act: 0.8924. Min Act: -0.0000

Data Index: 1856597 (The Pile)

Max Activating Token Index: 782

Text #17

Max Range: 1.1176. Min Range: -1.1176

Max Act: 0.7664. Min Act: -0.0000

Data Index: 9109 (The Pile)

Max Activating Token Index: 524

Text #18

Max Range: 1.1176. Min Range: -1.1176

Max Act: 0.8081. Min Act: -0.0000

Data Index: 1782337 (The Pile)

Max Activating Token Index: 438

Text #19

Max Range: 1.1176. Min Range: -1.1176

Max Act: 0.9209. Min Act: -0.0000

Data Index: 833388 (The Pile)

Max Activating Token Index: 879