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

Dataset: The Pile

Neuron 112 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1903975 (The Pile)

Max Activating Token Index: 333

Text #1

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.3114. Min Act: -0.0000

Data Index: 280286 (The Pile)

Max Activating Token Index: 787

Text #2

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1094134 (The Pile)

Max Activating Token Index: 854

Text #3

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1935555 (The Pile)

Max Activating Token Index: 586

Text #4

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1718871 (The Pile)

Max Activating Token Index: 773

Text #5

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.2461. Min Act: -0.0000

Data Index: 748236 (The Pile)

Max Activating Token Index: 790

Text #6

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.2505. Min Act: -0.0000

Data Index: 1048262 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.2459. Min Act: -0.0000

Data Index: 1259013 (The Pile)

Max Activating Token Index: 545

Text #8

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.2380. Min Act: -0.0000

Data Index: 988766 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.2285. Min Act: -0.0000

Data Index: 891727 (The Pile)

Max Activating Token Index: 209

Text #10

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.2247. Min Act: -0.0000

Data Index: 347450 (The Pile)

Max Activating Token Index: 994

Text #11

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.2269. Min Act: -0.0000

Data Index: 968010 (The Pile)

Max Activating Token Index: 950

Text #12

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.2489. Min Act: -0.0000

Data Index: 1578899 (The Pile)

Max Activating Token Index: 877

Text #13

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1825746 (The Pile)

Max Activating Token Index: 883

Text #14

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.2138. Min Act: -0.0000

Data Index: 756948 (The Pile)

Max Activating Token Index: 803

Text #15

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.2112. Min Act: -0.0000

Data Index: 639862 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.2257. Min Act: -0.0000

Data Index: 607012 (The Pile)

Max Activating Token Index: 936

Text #17

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.2259. Min Act: -0.0000

Data Index: 695744 (The Pile)

Max Activating Token Index: 1011

Text #18

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.2140. Min Act: -0.0000

Data Index: 76921 (The Pile)

Max Activating Token Index: 959

Text #19

Max Range: 0.4188. Min Range: -0.4188

Max Act: 0.2228. Min Act: -0.0000

Data Index: 318983 (The Pile)

Max Activating Token Index: 259