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

Dataset: The Pile

Neuron 1834 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: 0.6167. Min Range: -0.6167

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1747318 (The Pile)

Max Activating Token Index: 958

Text #1

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4874. Min Act: -0.0000

Data Index: 600366 (The Pile)

Max Activating Token Index: 984

Text #2

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4291. Min Act: -0.0000

Data Index: 1630245 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4174. Min Act: -0.0000

Data Index: 213711 (The Pile)

Max Activating Token Index: 507

Text #4

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4217. Min Act: -0.0000

Data Index: 415134 (The Pile)

Max Activating Token Index: 968

Text #5

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4028. Min Act: -0.0000

Data Index: 902626 (The Pile)

Max Activating Token Index: 759

Text #6

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.3682. Min Act: -0.0000

Data Index: 807951 (The Pile)

Max Activating Token Index: 111

Text #7

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1099592 (The Pile)

Max Activating Token Index: 188

Text #8

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.3945. Min Act: -0.0000

Data Index: 1999822 (The Pile)

Max Activating Token Index: 717

Text #9

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.3429. Min Act: -0.0000

Data Index: 179540 (The Pile)

Max Activating Token Index: 54

Text #10

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4084. Min Act: -0.0000

Data Index: 854810 (The Pile)

Max Activating Token Index: 116

Text #11

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.3770. Min Act: -0.0000

Data Index: 1146488 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.3749. Min Act: -0.0000

Data Index: 762208 (The Pile)

Max Activating Token Index: 629

Text #13

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.3817. Min Act: -0.0000

Data Index: 1024156 (The Pile)

Max Activating Token Index: 153

Text #14

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1513047 (The Pile)

Max Activating Token Index: 341

Text #15

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.3603. Min Act: -0.0000

Data Index: 668555 (The Pile)

Max Activating Token Index: 1004

Text #16

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.3421. Min Act: -0.0000

Data Index: 1682054 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1801948 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.3358. Min Act: -0.0000

Data Index: 429029 (The Pile)

Max Activating Token Index: 181

Text #19

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.3489. Min Act: -0.0000

Data Index: 474158 (The Pile)

Max Activating Token Index: 352