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

Dataset: The Pile

Neuron 2134 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: 5.8196. Min Range: -5.8196

Max Act: 5.8196. Min Act: -0.0000

Data Index: 1183795 (The Pile)

Max Activating Token Index: 458

Text #1

Max Range: 5.8196. Min Range: -5.8196

Max Act: 5.0785. Min Act: -0.0000

Data Index: 588769 (The Pile)

Max Activating Token Index: 756

Text #2

Max Range: 5.8196. Min Range: -5.8196

Max Act: 4.5863. Min Act: -0.0000

Data Index: 256390 (The Pile)

Max Activating Token Index: 696

Text #3

Max Range: 5.8196. Min Range: -5.8196

Max Act: 3.6330. Min Act: -0.0000

Data Index: 1302549 (The Pile)

Max Activating Token Index: 111

Text #4

Max Range: 5.8196. Min Range: -5.8196

Max Act: 3.3107. Min Act: -0.0000

Data Index: 640867 (The Pile)

Max Activating Token Index: 116

Text #5

Max Range: 5.8196. Min Range: -5.8196

Max Act: 3.7878. Min Act: -0.0000

Data Index: 359955 (The Pile)

Max Activating Token Index: 26

Text #6

Max Range: 5.8196. Min Range: -5.8196

Max Act: 3.4194. Min Act: -0.0000

Data Index: 1756018 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 5.8196. Min Range: -5.8196

Max Act: 3.1965. Min Act: -0.0000

Data Index: 1001062 (The Pile)

Max Activating Token Index: 720

Text #8

Max Range: 5.8196. Min Range: -5.8196

Max Act: 3.2906. Min Act: -0.0000

Data Index: 729712 (The Pile)

Max Activating Token Index: 479

Text #9

Max Range: 5.8196. Min Range: -5.8196

Max Act: 3.1341. Min Act: -0.0000

Data Index: 64014 (The Pile)

Max Activating Token Index: 119

Text #10

Max Range: 5.8196. Min Range: -5.8196

Max Act: 3.1320. Min Act: -0.0000

Data Index: 1555680 (The Pile)

Max Activating Token Index: 991

Text #11

Max Range: 5.8196. Min Range: -5.8196

Max Act: 3.5430. Min Act: -0.0000

Data Index: 1852430 (The Pile)

Max Activating Token Index: 341

Text #12

Max Range: 5.8196. Min Range: -5.8196

Max Act: 3.1739. Min Act: -0.0000

Data Index: 1075923 (The Pile)

Max Activating Token Index: 997

Text #13

Max Range: 5.8196. Min Range: -5.8196

Max Act: 3.0269. Min Act: -0.0000

Data Index: 69082 (The Pile)

Max Activating Token Index: 847

Text #14

Max Range: 5.8196. Min Range: -5.8196

Max Act: 2.9873. Min Act: -0.0000

Data Index: 396 (The Pile)

Max Activating Token Index: 882

Text #15

Max Range: 5.8196. Min Range: -5.8196

Max Act: 3.2976. Min Act: -0.0000

Data Index: 787022 (The Pile)

Max Activating Token Index: 114

Text #16

Max Range: 5.8196. Min Range: -5.8196

Max Act: 3.0945. Min Act: -0.0000

Data Index: 1248438 (The Pile)

Max Activating Token Index: 835

Text #17

Max Range: 5.8196. Min Range: -5.8196

Max Act: 3.0728. Min Act: -0.0000

Data Index: 1106448 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 5.8196. Min Range: -5.8196

Max Act: 2.9407. Min Act: -0.0000

Data Index: 777856 (The Pile)

Max Activating Token Index: 41

Text #19

Max Range: 5.8196. Min Range: -5.8196

Max Act: 3.1138. Min Act: -0.0000

Data Index: 1422450 (The Pile)

Max Activating Token Index: 35