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

Dataset: The Pile

Neuron 2355 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2948. Min Range: -1.2948

Max Act: 1.2948. Min Act: -0.0000

Data Index: 324163 (The Pile)

Max Activating Token Index: 228

Text #1

Max Range: 1.2948. Min Range: -1.2948

Max Act: 1.2119. Min Act: -0.0000

Data Index: 3458 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 1.2948. Min Range: -1.2948

Max Act: 1.1139. Min Act: -0.0000

Data Index: 1087011 (The Pile)

Max Activating Token Index: 270

Text #3

Max Range: 1.2948. Min Range: -1.2948

Max Act: 1.0726. Min Act: -0.0000

Data Index: 720006 (The Pile)

Max Activating Token Index: 947

Text #4

Max Range: 1.2948. Min Range: -1.2948

Max Act: 1.0471. Min Act: -0.0000

Data Index: 43077 (The Pile)

Max Activating Token Index: 80

Text #5

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.9992. Min Act: -0.0000

Data Index: 312805 (The Pile)

Max Activating Token Index: 137

Text #6

Max Range: 1.2948. Min Range: -1.2948

Max Act: 1.0204. Min Act: -0.0000

Data Index: 982236 (The Pile)

Max Activating Token Index: 788

Text #7

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.8911. Min Act: -0.0000

Data Index: 319225 (The Pile)

Max Activating Token Index: 646

Text #8

Max Range: 1.2948. Min Range: -1.2948

Max Act: 1.0059. Min Act: -0.0000

Data Index: 1774925 (The Pile)

Max Activating Token Index: 340

Text #9

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.9255. Min Act: -0.0000

Data Index: 1989605 (The Pile)

Max Activating Token Index: 77

Text #10

Max Range: 1.2948. Min Range: -1.2948

Max Act: 1.0291. Min Act: -0.0000

Data Index: 718944 (The Pile)

Max Activating Token Index: 1010

Text #11

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.9557. Min Act: -0.0000

Data Index: 1522049 (The Pile)

Max Activating Token Index: 91

Text #12

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.9048. Min Act: -0.0000

Data Index: 335069 (The Pile)

Max Activating Token Index: 208

Text #13

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.9010. Min Act: -0.0000

Data Index: 535679 (The Pile)

Max Activating Token Index: 858

Text #14

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.8819. Min Act: -0.0000

Data Index: 1271240 (The Pile)

Max Activating Token Index: 398

Text #15

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.8912. Min Act: -0.0000

Data Index: 261987 (The Pile)

Max Activating Token Index: 105

Text #16

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.9530. Min Act: -0.0000

Data Index: 1100821 (The Pile)

Max Activating Token Index: 336

Text #17

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.9448. Min Act: -0.0000

Data Index: 1655189 (The Pile)

Max Activating Token Index: 296

Text #18

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1275855 (The Pile)

Max Activating Token Index: 321

Text #19

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1269196 (The Pile)

Max Activating Token Index: 147