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

Dataset: The Pile

Neuron 3680 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: 0.9494. Min Range: -0.9494

Max Act: 0.9494. Min Act: -0.0000

Data Index: 1186565 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.9009. Min Act: -0.0000

Data Index: 525069 (The Pile)

Max Activating Token Index: 754

Text #2

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.9272. Min Act: -0.0000

Data Index: 204820 (The Pile)

Max Activating Token Index: 196

Text #3

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.8569. Min Act: -0.0000

Data Index: 518994 (The Pile)

Max Activating Token Index: 838

Text #4

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.8270. Min Act: -0.0000

Data Index: 214107 (The Pile)

Max Activating Token Index: 748

Text #5

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.8629. Min Act: -0.0000

Data Index: 1154582 (The Pile)

Max Activating Token Index: 794

Text #6

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.8082. Min Act: -0.0000

Data Index: 329165 (The Pile)

Max Activating Token Index: 461

Text #7

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.8086. Min Act: -0.0000

Data Index: 324590 (The Pile)

Max Activating Token Index: 519

Text #8

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.8446. Min Act: -0.0000

Data Index: 989112 (The Pile)

Max Activating Token Index: 486

Text #9

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.8138. Min Act: -0.0000

Data Index: 148902 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.7490. Min Act: -0.0000

Data Index: 58158 (The Pile)

Max Activating Token Index: 979

Text #11

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.7604. Min Act: -0.0000

Data Index: 1768938 (The Pile)

Max Activating Token Index: 89

Text #12

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.7943. Min Act: -0.0000

Data Index: 948586 (The Pile)

Max Activating Token Index: 280

Text #13

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1927458 (The Pile)

Max Activating Token Index: 220

Text #14

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.7974. Min Act: -0.0000

Data Index: 851349 (The Pile)

Max Activating Token Index: 201

Text #15

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.8001. Min Act: -0.0000

Data Index: 731505 (The Pile)

Max Activating Token Index: 962

Text #16

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1824214 (The Pile)

Max Activating Token Index: 681

Text #17

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.7211. Min Act: -0.0000

Data Index: 58937 (The Pile)

Max Activating Token Index: 982

Text #18

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.7287. Min Act: -0.0000

Data Index: 469325 (The Pile)

Max Activating Token Index: 495

Text #19

Max Range: 0.9494. Min Range: -0.9494

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1028011 (The Pile)

Max Activating Token Index: 959