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

Dataset: The Pile

Neuron 892 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.4161. Min Act: -0.0000

Data Index: 872158 (The Pile)

Max Activating Token Index: 394

Text #1

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3604. Min Act: -0.0000

Data Index: 250491 (The Pile)

Max Activating Token Index: 415

Text #2

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3680. Min Act: -0.0000

Data Index: 743049 (The Pile)

Max Activating Token Index: 276

Text #3

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1388987 (The Pile)

Max Activating Token Index: 543

Text #4

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3524. Min Act: -0.0000

Data Index: 1055469 (The Pile)

Max Activating Token Index: 216

Text #5

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3186. Min Act: -0.0000

Data Index: 1877835 (The Pile)

Max Activating Token Index: 28

Text #6

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3505. Min Act: -0.0000

Data Index: 605243 (The Pile)

Max Activating Token Index: 191

Text #7

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3113. Min Act: -0.0000

Data Index: 1067703 (The Pile)

Max Activating Token Index: 748

Text #8

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3238. Min Act: -0.0000

Data Index: 622061 (The Pile)

Max Activating Token Index: 92

Text #9

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.2970. Min Act: -0.0000

Data Index: 840689 (The Pile)

Max Activating Token Index: 992

Text #10

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3363. Min Act: -0.0000

Data Index: 281514 (The Pile)

Max Activating Token Index: 273

Text #11

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3375. Min Act: -0.0001

Data Index: 209015 (The Pile)

Max Activating Token Index: 231

Text #12

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1143702 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3270. Min Act: -0.0000

Data Index: 890416 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3297. Min Act: -0.0001

Data Index: 1396024 (The Pile)

Max Activating Token Index: 909

Text #15

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3180. Min Act: -0.0000

Data Index: 389083 (The Pile)

Max Activating Token Index: 549

Text #16

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1294333 (The Pile)

Max Activating Token Index: 117

Text #17

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3116. Min Act: -0.0000

Data Index: 85213 (The Pile)

Max Activating Token Index: 210

Text #18

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3223. Min Act: -0.0000

Data Index: 79504 (The Pile)

Max Activating Token Index: 52

Text #19

Max Range: 0.4161. Min Range: -0.4161

Max Act: 0.3305. Min Act: -0.0000

Data Index: 1660950 (The Pile)

Max Activating Token Index: 226