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

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

Neuron 2309 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.6578. Min Act: -0.0001

Data Index: 1234783 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.6166. Min Act: -0.0001

Data Index: 71476 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.5785. Min Act: -0.0001

Data Index: 481414 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.6101. Min Act: -0.0000

Data Index: 257896 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1299244 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.5883. Min Act: -0.0001

Data Index: 937272 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.5472. Min Act: -0.0000

Data Index: 1216387 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.5317. Min Act: -0.0001

Data Index: 739127 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.5539. Min Act: -0.0001

Data Index: 1016177 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1316581 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.5098. Min Act: -0.0000

Data Index: 945751 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.5059. Min Act: -0.0001

Data Index: 884655 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1188212 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4877. Min Act: -0.0000

Data Index: 61902 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4693. Min Act: -0.0001

Data Index: 118888 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.5000. Min Act: -0.0000

Data Index: 119469 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1354079 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.5118. Min Act: -0.0001

Data Index: 905044 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4952. Min Act: -0.0001

Data Index: 484109 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.6578. Min Range: -0.6578

Max Act: 0.4753. Min Act: -0.0000

Data Index: 980033 (C4 (Web Text))

Max Activating Token Index: 372