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

Dataset: The Pile

Neuron 3965 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1170406 (The Pile)

Max Activating Token Index: 164

Text #1

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4854. Min Act: -0.0000

Data Index: 378871 (The Pile)

Max Activating Token Index: 209

Text #2

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1482949 (The Pile)

Max Activating Token Index: 386

Text #3

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4763. Min Act: -0.0000

Data Index: 52576 (The Pile)

Max Activating Token Index: 306

Text #4

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4693. Min Act: -0.0000

Data Index: 1364533 (The Pile)

Max Activating Token Index: 23

Text #5

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.5197. Min Act: -0.0000

Data Index: 296262 (The Pile)

Max Activating Token Index: 102

Text #6

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4851. Min Act: -0.0000

Data Index: 580439 (The Pile)

Max Activating Token Index: 787

Text #7

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1184516 (The Pile)

Max Activating Token Index: 24

Text #8

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4484. Min Act: -0.0000

Data Index: 455733 (The Pile)

Max Activating Token Index: 64

Text #9

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3979. Min Act: -0.0000

Data Index: 21537 (The Pile)

Max Activating Token Index: 578

Text #10

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1159076 (The Pile)

Max Activating Token Index: 368

Text #11

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4070. Min Act: -0.0000

Data Index: 1626435 (The Pile)

Max Activating Token Index: 65

Text #12

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4340. Min Act: -0.0000

Data Index: 20481 (The Pile)

Max Activating Token Index: 188

Text #13

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1162290 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1737901 (The Pile)

Max Activating Token Index: 404

Text #15

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4288. Min Act: -0.0000

Data Index: 432562 (The Pile)

Max Activating Token Index: 872

Text #16

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1083015 (The Pile)

Max Activating Token Index: 350

Text #17

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4384. Min Act: -0.0000

Data Index: 283022 (The Pile)

Max Activating Token Index: 1005

Text #18

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3764. Min Act: -0.0000

Data Index: 1611288 (The Pile)

Max Activating Token Index: 96

Text #19

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3906. Min Act: -0.0000

Data Index: 498025 (The Pile)

Max Activating Token Index: 166