Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4427 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.6206. Min Act: -0.0000

Data Index: 1909979 (The Pile)

Max Activating Token Index: 147

Text #1

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.6206. Min Act: -0.0000

Data Index: 463665 (The Pile)

Max Activating Token Index: 147

Text #2

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.6206. Min Act: -0.0000

Data Index: 1029964 (The Pile)

Max Activating Token Index: 147

Text #3

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.6206. Min Act: -0.0000

Data Index: 1570176 (The Pile)

Max Activating Token Index: 147

Text #4

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.5012. Min Act: -0.0000

Data Index: 1786809 (The Pile)

Max Activating Token Index: 118

Text #5

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.5247. Min Act: -0.0000

Data Index: 1613917 (The Pile)

Max Activating Token Index: 168

Text #6

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.5317. Min Act: -0.0000

Data Index: 416260 (The Pile)

Max Activating Token Index: 86

Text #7

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4932. Min Act: -0.0000

Data Index: 186767 (The Pile)

Max Activating Token Index: 52

Text #8

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1398733 (The Pile)

Max Activating Token Index: 136

Text #9

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1705394 (The Pile)

Max Activating Token Index: 80

Text #10

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1180486 (The Pile)

Max Activating Token Index: 60

Text #11

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4157. Min Act: -0.0000

Data Index: 914721 (The Pile)

Max Activating Token Index: 377

Text #12

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4289. Min Act: -0.0000

Data Index: 1034609 (The Pile)

Max Activating Token Index: 64

Text #13

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4532. Min Act: -0.0000

Data Index: 992721 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4513. Min Act: -0.0000

Data Index: 97117 (The Pile)

Max Activating Token Index: 106

Text #15

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1518167 (The Pile)

Max Activating Token Index: 978

Text #16

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1352385 (The Pile)

Max Activating Token Index: 677

Text #17

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.3820. Min Act: -0.0000

Data Index: 1305938 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.3796. Min Act: -0.0000

Data Index: 693929 (The Pile)

Max Activating Token Index: 77

Text #19

Max Range: 0.6206. Min Range: -0.6206

Max Act: 0.4090. Min Act: -0.0000

Data Index: 1228487 (The Pile)

Max Activating Token Index: 276