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

Dataset: The Pile

Neuron 3729 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: 3.8648. Min Range: -3.8648

Max Act: 3.8648. Min Act: -0.0000

Data Index: 1840968 (The Pile)

Max Activating Token Index: 443

Text #1

Max Range: 3.8648. Min Range: -3.8648

Max Act: 3.4696. Min Act: -0.0000

Data Index: 267958 (The Pile)

Max Activating Token Index: 282

Text #2

Max Range: 3.8648. Min Range: -3.8648

Max Act: 3.4940. Min Act: -0.0000

Data Index: 1157757 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 3.8648. Min Range: -3.8648

Max Act: 3.4695. Min Act: -0.0000

Data Index: 1706830 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 3.8648. Min Range: -3.8648

Max Act: 3.3196. Min Act: -0.0000

Data Index: 1368223 (The Pile)

Max Activating Token Index: 140

Text #5

Max Range: 3.8648. Min Range: -3.8648

Max Act: 3.1524. Min Act: -0.0000

Data Index: 436346 (The Pile)

Max Activating Token Index: 225

Text #6

Max Range: 3.8648. Min Range: -3.8648

Max Act: 3.1294. Min Act: -0.0000

Data Index: 1382486 (The Pile)

Max Activating Token Index: 118

Text #7

Max Range: 3.8648. Min Range: -3.8648

Max Act: 3.3549. Min Act: -0.0000

Data Index: 1195394 (The Pile)

Max Activating Token Index: 986

Text #8

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.9085. Min Act: -0.0000

Data Index: 1179116 (The Pile)

Max Activating Token Index: 102

Text #9

Max Range: 3.8648. Min Range: -3.8648

Max Act: 3.1227. Min Act: -0.0000

Data Index: 670816 (The Pile)

Max Activating Token Index: 86

Text #10

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.8458. Min Act: -0.0000

Data Index: 801519 (The Pile)

Max Activating Token Index: 38

Text #11

Max Range: 3.8648. Min Range: -3.8648

Max Act: 3.1117. Min Act: -0.0000

Data Index: 700778 (The Pile)

Max Activating Token Index: 311

Text #12

Max Range: 3.8648. Min Range: -3.8648

Max Act: 3.1022. Min Act: -0.0000

Data Index: 1352899 (The Pile)

Max Activating Token Index: 466

Text #13

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.9821. Min Act: -0.0000

Data Index: 1605322 (The Pile)

Max Activating Token Index: 226

Text #14

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.9377. Min Act: -0.0000

Data Index: 1028550 (The Pile)

Max Activating Token Index: 103

Text #15

Max Range: 3.8648. Min Range: -3.8648

Max Act: 3.2977. Min Act: -0.0000

Data Index: 1090254 (The Pile)

Max Activating Token Index: 91

Text #16

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.8933. Min Act: -0.0000

Data Index: 938889 (The Pile)

Max Activating Token Index: 276

Text #17

Max Range: 3.8648. Min Range: -3.8648

Max Act: 3.0171. Min Act: -0.0000

Data Index: 581679 (The Pile)

Max Activating Token Index: 40

Text #18

Max Range: 3.8648. Min Range: -3.8648

Max Act: 2.9698. Min Act: -0.0000

Data Index: 695362 (The Pile)

Max Activating Token Index: 137

Text #19

Max Range: 3.8648. Min Range: -3.8648

Max Act: 3.1075. Min Act: -0.0000

Data Index: 1825966 (The Pile)

Max Activating Token Index: 921