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

Dataset: The Pile

Neuron 2983 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: 0.7174. Min Range: -0.7174

Max Act: 0.7174. Min Act: -0.0000

Data Index: 1993493 (The Pile)

Max Activating Token Index: 23

Text #1

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1181173 (The Pile)

Max Activating Token Index: 669

Text #2

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.6647. Min Act: -0.0000

Data Index: 1121371 (The Pile)

Max Activating Token Index: 829

Text #3

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.6210. Min Act: -0.0000

Data Index: 414485 (The Pile)

Max Activating Token Index: 538

Text #4

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1168943 (The Pile)

Max Activating Token Index: 518

Text #5

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.6075. Min Act: -0.0000

Data Index: 967333 (The Pile)

Max Activating Token Index: 251

Text #6

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.6125. Min Act: -0.0000

Data Index: 109452 (The Pile)

Max Activating Token Index: 28

Text #7

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.6114. Min Act: -0.0000

Data Index: 1403040 (The Pile)

Max Activating Token Index: 178

Text #8

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5905. Min Act: -0.0000

Data Index: 856415 (The Pile)

Max Activating Token Index: 16

Text #9

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1970618 (The Pile)

Max Activating Token Index: 575

Text #10

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1367953 (The Pile)

Max Activating Token Index: 402

Text #11

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5751. Min Act: -0.0000

Data Index: 183775 (The Pile)

Max Activating Token Index: 544

Text #12

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5601. Min Act: -0.0000

Data Index: 3235 (The Pile)

Max Activating Token Index: 267

Text #13

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5717. Min Act: -0.0000

Data Index: 620435 (The Pile)

Max Activating Token Index: 551

Text #14

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1662468 (The Pile)

Max Activating Token Index: 54

Text #15

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5722. Min Act: -0.0000

Data Index: 1224976 (The Pile)

Max Activating Token Index: 629

Text #16

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1822923 (The Pile)

Max Activating Token Index: 564

Text #17

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5360. Min Act: -0.0000

Data Index: 152215 (The Pile)

Max Activating Token Index: 617

Text #18

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5677. Min Act: -0.0000

Data Index: 506754 (The Pile)

Max Activating Token Index: 28

Text #19

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1104668 (The Pile)

Max Activating Token Index: 135