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

Dataset: The Pile

Neuron 2683 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: 3.3386. Min Range: -3.3386

Max Act: 3.2035. Min Act: -0.0000

Data Index: 40865 (The Pile)

Max Activating Token Index: 88

Text #1

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.3386. Min Act: -0.0000

Data Index: 1471291 (The Pile)

Max Activating Token Index: 301

Text #2

Max Range: 3.3386. Min Range: -3.3386

Max Act: 2.8927. Min Act: -0.0000

Data Index: 1801177 (The Pile)

Max Activating Token Index: 882

Text #3

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.0595. Min Act: -0.0000

Data Index: 1832087 (The Pile)

Max Activating Token Index: 426

Text #4

Max Range: 3.3386. Min Range: -3.3386

Max Act: 3.3031. Min Act: -0.0000

Data Index: 288108 (The Pile)

Max Activating Token Index: 630

Text #5

Max Range: 3.3386. Min Range: -3.3386

Max Act: 2.7890. Min Act: -0.0000

Data Index: 176089 (The Pile)

Max Activating Token Index: 707

Text #6

Max Range: 3.3386. Min Range: -3.3386

Max Act: 2.9115. Min Act: -0.0000

Data Index: 1420221 (The Pile)

Max Activating Token Index: 483

Text #7

Max Range: 3.3386. Min Range: -3.3386

Max Act: 2.7273. Min Act: -0.0000

Data Index: 778187 (The Pile)

Max Activating Token Index: 849

Text #8

Max Range: 3.3386. Min Range: -3.3386

Max Act: 2.7158. Min Act: -0.0000

Data Index: 238609 (The Pile)

Max Activating Token Index: 768

Text #9

Max Range: 3.3386. Min Range: -3.3386

Max Act: 2.7832. Min Act: -0.0000

Data Index: 1576139 (The Pile)

Max Activating Token Index: 7

Text #10

Max Range: 3.3386. Min Range: -3.3386

Max Act: 2.6145. Min Act: -0.0000

Data Index: 1879608 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 3.3386. Min Range: -3.3386

Max Act: 2.7278. Min Act: -0.0000

Data Index: 796430 (The Pile)

Max Activating Token Index: 486

Text #12

Max Range: 3.3386. Min Range: -3.3386

Max Act: 2.6968. Min Act: -0.0000

Data Index: 378305 (The Pile)

Max Activating Token Index: 512

Text #13

Max Range: 3.3386. Min Range: -3.3386

Max Act: 2.3137. Min Act: -0.0000

Data Index: 1288236 (The Pile)

Max Activating Token Index: 49

Text #14

Max Range: 3.3386. Min Range: -3.3386

Max Act: 2.6864. Min Act: -0.0000

Data Index: 1536318 (The Pile)

Max Activating Token Index: 323

Text #15

Max Range: 3.3386. Min Range: -3.3386

Max Act: 2.7830. Min Act: -0.0000

Data Index: 310358 (The Pile)

Max Activating Token Index: 699

Text #16

Max Range: 3.3386. Min Range: -3.3386

Max Act: 2.6500. Min Act: -0.0000

Data Index: 1436286 (The Pile)

Max Activating Token Index: 928

Text #17

Max Range: 3.3386. Min Range: -3.3386

Max Act: 2.6180. Min Act: -0.0000

Data Index: 1043677 (The Pile)

Max Activating Token Index: 217

Text #18

Max Range: 3.3386. Min Range: -3.3386

Max Act: 2.4870. Min Act: -0.0000

Data Index: 957958 (The Pile)

Max Activating Token Index: 856

Text #19

Max Range: 3.3386. Min Range: -3.3386

Max Act: 2.4530. Min Act: -0.0000

Data Index: 1387493 (The Pile)

Max Activating Token Index: 323