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

Dataset: The Pile

Neuron 4785 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.2159. Min Act: -0.0000

Data Index: 416576 (The Pile)

Max Activating Token Index: 182

Text #1

Max Range: 1.2159. Min Range: -1.2159

Max Act: 1.0297. Min Act: -0.0000

Data Index: 1385532 (The Pile)

Max Activating Token Index: 38

Text #2

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.9047. Min Act: -0.0000

Data Index: 45712 (The Pile)

Max Activating Token Index: 173

Text #3

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8411. Min Act: 0.0000

Data Index: 1337345 (The Pile)

Max Activating Token Index: 204

Text #4

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8191. Min Act: -0.0000

Data Index: 1709042 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.8557. Min Act: -0.0000

Data Index: 509051 (The Pile)

Max Activating Token Index: 44

Text #6

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.7443. Min Act: -0.0000

Data Index: 1293466 (The Pile)

Max Activating Token Index: 604

Text #7

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.7340. Min Act: -0.0000

Data Index: 1113791 (The Pile)

Max Activating Token Index: 121

Text #8

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1252511 (The Pile)

Max Activating Token Index: 940

Text #9

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.7245. Min Act: -0.0000

Data Index: 1445939 (The Pile)

Max Activating Token Index: 909

Text #10

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.7274. Min Act: -0.0000

Data Index: 536361 (The Pile)

Max Activating Token Index: 623

Text #11

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.7108. Min Act: -0.0000

Data Index: 314799 (The Pile)

Max Activating Token Index: 78

Text #12

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.6574. Min Act: -0.0000

Data Index: 498189 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1234988 (The Pile)

Max Activating Token Index: 448

Text #14

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.6513. Min Act: -0.0000

Data Index: 161076 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1921735 (The Pile)

Max Activating Token Index: 919

Text #16

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1152692 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.6494. Min Act: -0.0000

Data Index: 793054 (The Pile)

Max Activating Token Index: 128

Text #18

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.6152. Min Act: -0.0000

Data Index: 385811 (The Pile)

Max Activating Token Index: 648

Text #19

Max Range: 1.2159. Min Range: -1.2159

Max Act: 0.6163. Min Act: -0.0000

Data Index: 447157 (The Pile)

Max Activating Token Index: 568