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

Dataset: The Pile

Neuron 3205 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0189. Min Range: -3.0189

Max Act: 3.0189. Min Act: -0.0000

Data Index: 91634 (The Pile)

Max Activating Token Index: 1010

Text #1

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.6091. Min Act: -0.0000

Data Index: 340495 (The Pile)

Max Activating Token Index: 894

Text #2

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.8231. Min Act: -0.0000

Data Index: 1878255 (The Pile)

Max Activating Token Index: 15

Text #3

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.8185. Min Act: -0.0000

Data Index: 470936 (The Pile)

Max Activating Token Index: 174

Text #4

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.1629. Min Act: -0.0000

Data Index: 191260 (The Pile)

Max Activating Token Index: 53

Text #5

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.6438. Min Act: -0.0000

Data Index: 1401468 (The Pile)

Max Activating Token Index: 46

Text #6

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.6885. Min Act: -0.0000

Data Index: 653080 (The Pile)

Max Activating Token Index: 123

Text #7

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.2890. Min Act: -0.0000

Data Index: 509181 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.5281. Min Act: -0.0000

Data Index: 511332 (The Pile)

Max Activating Token Index: 793

Text #9

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.5641. Min Act: -0.0000

Data Index: 485276 (The Pile)

Max Activating Token Index: 1019

Text #10

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.2597. Min Act: -0.0000

Data Index: 1078286 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.1921. Min Act: -0.0000

Data Index: 588840 (The Pile)

Max Activating Token Index: 178

Text #12

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.4001. Min Act: -0.0000

Data Index: 1886057 (The Pile)

Max Activating Token Index: 572

Text #13

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.3240. Min Act: -0.0000

Data Index: 1985167 (The Pile)

Max Activating Token Index: 151

Text #14

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.2455. Min Act: -0.0000

Data Index: 1254398 (The Pile)

Max Activating Token Index: 678

Text #15

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.3050. Min Act: -0.0000

Data Index: 429195 (The Pile)

Max Activating Token Index: 839

Text #16

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.4207. Min Act: -0.0000

Data Index: 1339478 (The Pile)

Max Activating Token Index: 150

Text #17

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.2214. Min Act: -0.0000

Data Index: 1439951 (The Pile)

Max Activating Token Index: 227

Text #18

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.2096. Min Act: -0.0000

Data Index: 248644 (The Pile)

Max Activating Token Index: 795

Text #19

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.2147. Min Act: -0.0000

Data Index: 350875 (The Pile)

Max Activating Token Index: 662