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

Dataset: The Pile

Neuron 212 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.8033. Min Act: -0.0000

Data Index: 36004 (The Pile)

Max Activating Token Index: 341

Text #1

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.8429. Min Act: -0.0000

Data Index: 1219033 (The Pile)

Max Activating Token Index: 462

Text #2

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.6111. Min Act: -0.0000

Data Index: 1503636 (The Pile)

Max Activating Token Index: 231

Text #3

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.5961. Min Act: -0.0000

Data Index: 1524511 (The Pile)

Max Activating Token Index: 249

Text #4

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.5066. Min Act: -0.0000

Data Index: 312554 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.3440. Min Act: -0.0000

Data Index: 45472 (The Pile)

Max Activating Token Index: 121

Text #6

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.4196. Min Act: -0.0000

Data Index: 218051 (The Pile)

Max Activating Token Index: 474

Text #7

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.3894. Min Act: -0.0000

Data Index: 81463 (The Pile)

Max Activating Token Index: 278

Text #8

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.2609. Min Act: -0.0000

Data Index: 1556044 (The Pile)

Max Activating Token Index: 55

Text #9

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.3766. Min Act: -0.0000

Data Index: 642534 (The Pile)

Max Activating Token Index: 132

Text #10

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.3731. Min Act: -0.0000

Data Index: 1216343 (The Pile)

Max Activating Token Index: 148

Text #11

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.2648. Min Act: -0.0000

Data Index: 156928 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.0625. Min Act: -0.0000

Data Index: 619943 (The Pile)

Max Activating Token Index: 394

Text #13

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.2200. Min Act: -0.0000

Data Index: 1507169 (The Pile)

Max Activating Token Index: 660

Text #14

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.2271. Min Act: -0.0000

Data Index: 940532 (The Pile)

Max Activating Token Index: 304

Text #15

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.1420. Min Act: -0.0000

Data Index: 283907 (The Pile)

Max Activating Token Index: 39

Text #16

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.0670. Min Act: -0.0000

Data Index: 1447685 (The Pile)

Max Activating Token Index: 348

Text #17

Max Range: 3.8429. Min Range: -3.8429

Max Act: 2.9170. Min Act: -0.0000

Data Index: 820440 (The Pile)

Max Activating Token Index: 72

Text #18

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.0416. Min Act: -0.0000

Data Index: 242029 (The Pile)

Max Activating Token Index: 229

Text #19

Max Range: 3.8429. Min Range: -3.8429

Max Act: 3.0209. Min Act: -0.0000

Data Index: 118397 (The Pile)

Max Activating Token Index: 993