Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3792 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.1773. Min Act: -0.0000

Data Index: 88504 (The Pile)

Max Activating Token Index: 684

Text #1

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.3333. Min Act: -0.0000

Data Index: 1036897 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.0708. Min Act: -0.0000

Data Index: 288885 (The Pile)

Max Activating Token Index: 573

Text #3

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.0701. Min Act: -0.0000

Data Index: 946981 (The Pile)

Max Activating Token Index: 204

Text #4

Max Range: 1.3333. Min Range: -1.3333

Max Act: 0.8314. Min Act: -0.0000

Data Index: 654361 (The Pile)

Max Activating Token Index: 50

Text #5

Max Range: 1.3333. Min Range: -1.3333

Max Act: 0.8075. Min Act: -0.0000

Data Index: 239987 (The Pile)

Max Activating Token Index: 962

Text #6

Max Range: 1.3333. Min Range: -1.3333

Max Act: 0.9693. Min Act: -0.0000

Data Index: 1706802 (The Pile)

Max Activating Token Index: 334

Text #7

Max Range: 1.3333. Min Range: -1.3333

Max Act: 0.7258. Min Act: -0.0000

Data Index: 323382 (The Pile)

Max Activating Token Index: 695

Text #8

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.0559. Min Act: -0.0000

Data Index: 444400 (The Pile)

Max Activating Token Index: 490

Text #9

Max Range: 1.3333. Min Range: -1.3333

Max Act: 0.7988. Min Act: -0.0000

Data Index: 593903 (The Pile)

Max Activating Token Index: 653

Text #10

Max Range: 1.3333. Min Range: -1.3333

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1258978 (The Pile)

Max Activating Token Index: 303

Text #11

Max Range: 1.3333. Min Range: -1.3333

Max Act: 0.8727. Min Act: -0.0000

Data Index: 1289782 (The Pile)

Max Activating Token Index: 986

Text #12

Max Range: 1.3333. Min Range: -1.3333

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1117329 (The Pile)

Max Activating Token Index: 592

Text #13

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1241142 (The Pile)

Max Activating Token Index: 398

Text #14

Max Range: 1.3333. Min Range: -1.3333

Max Act: 0.8487. Min Act: -0.0000

Data Index: 1173701 (The Pile)

Max Activating Token Index: 174

Text #15

Max Range: 1.3333. Min Range: -1.3333

Max Act: 0.8825. Min Act: -0.0000

Data Index: 1759318 (The Pile)

Max Activating Token Index: 486

Text #16

Max Range: 1.3333. Min Range: -1.3333

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1177681 (The Pile)

Max Activating Token Index: 580

Text #17

Max Range: 1.3333. Min Range: -1.3333

Max Act: 0.9294. Min Act: -0.0000

Data Index: 167134 (The Pile)

Max Activating Token Index: 473

Text #18

Max Range: 1.3333. Min Range: -1.3333

Max Act: 0.8050. Min Act: -0.0000

Data Index: 1216067 (The Pile)

Max Activating Token Index: 721

Text #19

Max Range: 1.3333. Min Range: -1.3333

Max Act: 0.8147. Min Act: -0.0000

Data Index: 980140 (The Pile)

Max Activating Token Index: 423