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

Dataset: The Pile

Neuron 473 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: 1.6414. Min Range: -1.6414

Max Act: 1.6414. Min Act: -0.0000

Data Index: 1383089 (The Pile)

Max Activating Token Index: 128

Text #1

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.6372. Min Act: -0.0000

Data Index: 1220219 (The Pile)

Max Activating Token Index: 201

Text #2

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.6054. Min Act: -0.0000

Data Index: 764809 (The Pile)

Max Activating Token Index: 108

Text #3

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.5046. Min Act: -0.0000

Data Index: 1354309 (The Pile)

Max Activating Token Index: 253

Text #4

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.5588. Min Act: -0.0000

Data Index: 918648 (The Pile)

Max Activating Token Index: 61

Text #5

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.5182. Min Act: -0.0000

Data Index: 791614 (The Pile)

Max Activating Token Index: 19

Text #6

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.4937. Min Act: -0.0000

Data Index: 1127664 (The Pile)

Max Activating Token Index: 436

Text #7

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.4423. Min Act: -0.0000

Data Index: 1965626 (The Pile)

Max Activating Token Index: 164

Text #8

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.5073. Min Act: -0.0000

Data Index: 1726091 (The Pile)

Max Activating Token Index: 206

Text #9

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.5122. Min Act: -0.0000

Data Index: 847968 (The Pile)

Max Activating Token Index: 420

Text #10

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.5521. Min Act: -0.0000

Data Index: 1983328 (The Pile)

Max Activating Token Index: 538

Text #11

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.4462. Min Act: -0.0000

Data Index: 33827 (The Pile)

Max Activating Token Index: 219

Text #12

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.4970. Min Act: -0.0000

Data Index: 201098 (The Pile)

Max Activating Token Index: 914

Text #13

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.4417. Min Act: -0.0000

Data Index: 905490 (The Pile)

Max Activating Token Index: 184

Text #14

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.4216. Min Act: -0.0000

Data Index: 456504 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.4869. Min Act: -0.0000

Data Index: 207518 (The Pile)

Max Activating Token Index: 134

Text #16

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.4652. Min Act: -0.0000

Data Index: 1031056 (The Pile)

Max Activating Token Index: 486

Text #17

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.4222. Min Act: -0.0000

Data Index: 566205 (The Pile)

Max Activating Token Index: 243

Text #18

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.3973. Min Act: -0.0000

Data Index: 1948570 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 1.6414. Min Range: -1.6414

Max Act: 1.3509. Min Act: -0.0000

Data Index: 608018 (The Pile)

Max Activating Token Index: 1023