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

Dataset: The Pile

Neuron 1558 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.7188. Min Act: -0.0000

Data Index: 643899 (The Pile)

Max Activating Token Index: 611

Text #1

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6916. Min Act: -0.0000

Data Index: 747079 (The Pile)

Max Activating Token Index: 953

Text #2

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1119250 (The Pile)

Max Activating Token Index: 463

Text #3

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6601. Min Act: -0.0000

Data Index: 411745 (The Pile)

Max Activating Token Index: 136

Text #4

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.7010. Min Act: 0.0000

Data Index: 1087495 (The Pile)

Max Activating Token Index: 753

Text #5

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6740. Min Act: -0.0000

Data Index: 244269 (The Pile)

Max Activating Token Index: 270

Text #6

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1312760 (The Pile)

Max Activating Token Index: 82

Text #7

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1706680 (The Pile)

Max Activating Token Index: 682

Text #8

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5791. Min Act: -0.0000

Data Index: 514024 (The Pile)

Max Activating Token Index: 325

Text #9

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6475. Min Act: -0.0000

Data Index: 1302053 (The Pile)

Max Activating Token Index: 185

Text #10

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6032. Min Act: -0.0000

Data Index: 779381 (The Pile)

Max Activating Token Index: 272

Text #11

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1460904 (The Pile)

Max Activating Token Index: 206

Text #12

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5755. Min Act: -0.0000

Data Index: 930897 (The Pile)

Max Activating Token Index: 59

Text #13

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6123. Min Act: -0.0000

Data Index: 111510 (The Pile)

Max Activating Token Index: 117

Text #14

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5337. Min Act: -0.0000

Data Index: 1161470 (The Pile)

Max Activating Token Index: 154

Text #15

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6274. Min Act: -0.0000

Data Index: 154521 (The Pile)

Max Activating Token Index: 144

Text #16

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1404711 (The Pile)

Max Activating Token Index: 615

Text #17

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1511737 (The Pile)

Max Activating Token Index: 48

Text #18

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5408. Min Act: -0.0000

Data Index: 929054 (The Pile)

Max Activating Token Index: 292

Text #19

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5431. Min Act: -0.0000

Data Index: 743547 (The Pile)

Max Activating Token Index: 925