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

Dataset: The Pile

Neuron 2575 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: 0.3163. Min Range: -0.3163

Max Act: 0.3163. Min Act: -0.0000

Data Index: 268944 (The Pile)

Max Activating Token Index: 164

Text #1

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2749. Min Act: -0.0000

Data Index: 1987118 (The Pile)

Max Activating Token Index: 724

Text #2

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1838439 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2714. Min Act: -0.0000

Data Index: 1616219 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2494. Min Act: -0.0000

Data Index: 1865915 (The Pile)

Max Activating Token Index: 58

Text #5

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2573. Min Act: -0.0000

Data Index: 1578479 (The Pile)

Max Activating Token Index: 673

Text #6

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2448. Min Act: -0.0000

Data Index: 435890 (The Pile)

Max Activating Token Index: 142

Text #7

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1552974 (The Pile)

Max Activating Token Index: 413

Text #8

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2320. Min Act: -0.0000

Data Index: 1212637 (The Pile)

Max Activating Token Index: 942

Text #9

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2484. Min Act: -0.0000

Data Index: 79053 (The Pile)

Max Activating Token Index: 119

Text #10

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1764972 (The Pile)

Max Activating Token Index: 786

Text #11

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2199. Min Act: -0.0000

Data Index: 742825 (The Pile)

Max Activating Token Index: 470

Text #12

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2171. Min Act: -0.0000

Data Index: 1296584 (The Pile)

Max Activating Token Index: 338

Text #13

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1409157 (The Pile)

Max Activating Token Index: 327

Text #14

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2007. Min Act: -0.0000

Data Index: 608217 (The Pile)

Max Activating Token Index: 992

Text #15

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2135. Min Act: -0.0000

Data Index: 1859775 (The Pile)

Max Activating Token Index: 668

Text #16

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2162. Min Act: -0.0000

Data Index: 1602240 (The Pile)

Max Activating Token Index: 30

Text #17

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1012499 (The Pile)

Max Activating Token Index: 354

Text #18

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2036. Min Act: -0.0000

Data Index: 999318 (The Pile)

Max Activating Token Index: 385

Text #19

Max Range: 0.3163. Min Range: -0.3163

Max Act: 0.2322. Min Act: -0.0000

Data Index: 807569 (The Pile)

Max Activating Token Index: 54