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

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

Neuron 430 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.4053. Min Act: -0.0000

Data Index: 12033 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.4129. Min Act: -0.0000

Data Index: 300427 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.4108. Min Act: -0.0000

Data Index: 502216 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.4046. Min Act: -0.0000

Data Index: 478508 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.4272. Min Act: -0.0000

Data Index: 724762 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.3908. Min Act: -0.0000

Data Index: 1094713 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.3871. Min Act: -0.0000

Data Index: 738030 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.3690. Min Act: -0.0000

Data Index: 332338 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.3756. Min Act: -0.0000

Data Index: 77143 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1261671 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1330626 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.3498. Min Act: -0.0000

Data Index: 522943 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.3760. Min Act: -0.0000

Data Index: 79656 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1272707 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.3759. Min Act: -0.0000

Data Index: 1227205 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.3578. Min Act: -0.0000

Data Index: 75337 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.3574. Min Act: -0.0000

Data Index: 543213 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1327826 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.3311. Min Act: -0.0000

Data Index: 148766 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.4272. Min Range: -0.4272

Max Act: 0.3512. Min Act: -0.0000

Data Index: 1033129 (C4 (Web Text))

Max Activating Token Index: 416