Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 217 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5879. Min Act: -0.0000

Data Index: 902313 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5682. Min Act: -0.0000

Data Index: 108445 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5542. Min Act: -0.0000

Data Index: 460730 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5422. Min Act: -0.0000

Data Index: 1173873 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5209. Min Act: -0.0000

Data Index: 719585 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5167. Min Act: 0.0000

Data Index: 183414 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4929. Min Act: -0.0000

Data Index: 360794 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4748. Min Act: -0.0000

Data Index: 438501 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4682. Min Act: -0.0000

Data Index: 1336152 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4299. Min Act: -0.0000

Data Index: 118742 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4413. Min Act: -0.0000

Data Index: 148473 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4159. Min Act: -0.0000

Data Index: 916604 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4127. Min Act: -0.0000

Data Index: 1296294 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1094931 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4160. Min Act: -0.0000

Data Index: 128961 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1268533 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1188107 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3596. Min Act: -0.0000

Data Index: 95192 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3682. Min Act: -0.0000

Data Index: 471998 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.3762. Min Act: -0.0000

Data Index: 695209 (C4 (Web Text))

Max Activating Token Index: 61