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

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

Neuron 2873 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: 0.5096. Min Range: -0.5096

Max Act: 0.5096. Min Act: -0.0001

Data Index: 223112 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.4398. Min Act: -0.0001

Data Index: 1106127 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.4213. Min Act: -0.0000

Data Index: 378905 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.4299. Min Act: -0.0001

Data Index: 1266517 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.4114. Min Act: -0.0001

Data Index: 116324 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.4228. Min Act: -0.0000

Data Index: 371117 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3678. Min Act: -0.0001

Data Index: 603761 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.4040. Min Act: -0.0001

Data Index: 596023 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.4231. Min Act: -0.0000

Data Index: 86168 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3961. Min Act: -0.0000

Data Index: 160074 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.4089. Min Act: -0.0000

Data Index: 1231454 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3705. Min Act: -0.0001

Data Index: 635215 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3889. Min Act: -0.0001

Data Index: 1259419 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3756. Min Act: -0.0001

Data Index: 780758 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3758. Min Act: -0.0001

Data Index: 1010407 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3705. Min Act: -0.0000

Data Index: 708700 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3783. Min Act: -0.0001

Data Index: 552885 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3784. Min Act: -0.0001

Data Index: 168046 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3786. Min Act: -0.0000

Data Index: 538192 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.5096. Min Range: -0.5096

Max Act: 0.3772. Min Act: -0.0001

Data Index: 817522 (C4 (Web Text))

Max Activating Token Index: 940