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

Dataset: The Pile

Neuron 3056 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: 0.5222. Min Range: -0.5222

Max Act: 0.5222. Min Act: -0.0000

Data Index: 1972136 (The Pile)

Max Activating Token Index: 206

Text #1

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.5011. Min Act: -0.0000

Data Index: 285074 (The Pile)

Max Activating Token Index: 16

Text #2

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1360546 (The Pile)

Max Activating Token Index: 20

Text #3

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1790610 (The Pile)

Max Activating Token Index: 226

Text #4

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4099. Min Act: -0.0000

Data Index: 742703 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1186191 (The Pile)

Max Activating Token Index: 311

Text #6

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1501153 (The Pile)

Max Activating Token Index: 174

Text #7

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1757863 (The Pile)

Max Activating Token Index: 973

Text #8

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4200. Min Act: -0.0000

Data Index: 1144054 (The Pile)

Max Activating Token Index: 491

Text #9

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4245. Min Act: -0.0000

Data Index: 724208 (The Pile)

Max Activating Token Index: 210

Text #10

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3929. Min Act: -0.0000

Data Index: 438424 (The Pile)

Max Activating Token Index: 626

Text #11

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4048. Min Act: -0.0000

Data Index: 853639 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3911. Min Act: -0.0000

Data Index: 1374109 (The Pile)

Max Activating Token Index: 108

Text #13

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1888713 (The Pile)

Max Activating Token Index: 615

Text #14

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3694. Min Act: -0.0000

Data Index: 62866 (The Pile)

Max Activating Token Index: 13

Text #15

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3772. Min Act: -0.0000

Data Index: 1647025 (The Pile)

Max Activating Token Index: 92

Text #16

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1421481 (The Pile)

Max Activating Token Index: 866

Text #17

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3886. Min Act: -0.0000

Data Index: 271133 (The Pile)

Max Activating Token Index: 57

Text #18

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3971. Min Act: -0.0000

Data Index: 1687471 (The Pile)

Max Activating Token Index: 526

Text #19

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.3996. Min Act: -0.0000

Data Index: 1557536 (The Pile)

Max Activating Token Index: 413