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

Dataset: The Pile

Neuron 2850 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: 1.2968. Min Range: -1.2968

Max Act: 1.2968. Min Act: -0.0000

Data Index: 469987 (The Pile)

Max Activating Token Index: 461

Text #1

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.1252. Min Act: -0.0000

Data Index: 1800270 (The Pile)

Max Activating Token Index: 544

Text #2

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.0820. Min Act: -0.0000

Data Index: 1124876 (The Pile)

Max Activating Token Index: 984

Text #3

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.0056. Min Act: -0.0000

Data Index: 211969 (The Pile)

Max Activating Token Index: 628

Text #4

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.0345. Min Act: -0.0000

Data Index: 1951871 (The Pile)

Max Activating Token Index: 183

Text #5

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.9898. Min Act: -0.0000

Data Index: 265207 (The Pile)

Max Activating Token Index: 379

Text #6

Max Range: 1.2968. Min Range: -1.2968

Max Act: 1.0176. Min Act: -0.0000

Data Index: 1129432 (The Pile)

Max Activating Token Index: 478

Text #7

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1165394 (The Pile)

Max Activating Token Index: 663

Text #8

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.9415. Min Act: -0.0000

Data Index: 203165 (The Pile)

Max Activating Token Index: 658

Text #9

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.9301. Min Act: -0.0000

Data Index: 1606819 (The Pile)

Max Activating Token Index: 411

Text #10

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.8958. Min Act: -0.0000

Data Index: 231921 (The Pile)

Max Activating Token Index: 590

Text #11

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.9446. Min Act: -0.0000

Data Index: 1765129 (The Pile)

Max Activating Token Index: 345

Text #12

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.9298. Min Act: -0.0000

Data Index: 530400 (The Pile)

Max Activating Token Index: 630

Text #13

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.9030. Min Act: -0.0000

Data Index: 409940 (The Pile)

Max Activating Token Index: 730

Text #14

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.9212. Min Act: -0.0000

Data Index: 1987446 (The Pile)

Max Activating Token Index: 469

Text #15

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.9363. Min Act: -0.0000

Data Index: 550423 (The Pile)

Max Activating Token Index: 920

Text #16

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1130950 (The Pile)

Max Activating Token Index: 472

Text #17

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.9373. Min Act: -0.0000

Data Index: 1180508 (The Pile)

Max Activating Token Index: 482

Text #18

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.8663. Min Act: -0.0000

Data Index: 532355 (The Pile)

Max Activating Token Index: 271

Text #19

Max Range: 1.2968. Min Range: -1.2968

Max Act: 0.8931. Min Act: -0.0000

Data Index: 339112 (The Pile)

Max Activating Token Index: 409