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

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

Neuron 2679 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3317. Min Range: -1.3317

Max Act: 1.2928. Min Act: -0.0001

Data Index: 1294618 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 1.3317. Min Range: -1.3317

Max Act: 1.3317. Min Act: -0.0000

Data Index: 257371 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 1.3317. Min Range: -1.3317

Max Act: 1.3052. Min Act: -0.0000

Data Index: 571927 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 1.3317. Min Range: -1.3317

Max Act: 1.2412. Min Act: -0.0000

Data Index: 48509 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 1.3317. Min Range: -1.3317

Max Act: 1.1782. Min Act: -0.0000

Data Index: 205246 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 1.3317. Min Range: -1.3317

Max Act: 1.1655. Min Act: -0.0000

Data Index: 941332 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 1.3317. Min Range: -1.3317

Max Act: 1.0694. Min Act: -0.0000

Data Index: 563784 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 1.3317. Min Range: -1.3317

Max Act: 0.9850. Min Act: -0.0000

Data Index: 214541 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 1.3317. Min Range: -1.3317

Max Act: 1.0190. Min Act: -0.0000

Data Index: 619468 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 1.3317. Min Range: -1.3317

Max Act: 1.0164. Min Act: -0.0000

Data Index: 908161 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 1.3317. Min Range: -1.3317

Max Act: 0.9735. Min Act: -0.0000

Data Index: 180020 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 1.3317. Min Range: -1.3317

Max Act: 0.9969. Min Act: -0.0001

Data Index: 259043 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 1.3317. Min Range: -1.3317

Max Act: 0.9539. Min Act: -0.0001

Data Index: 371449 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 1.3317. Min Range: -1.3317

Max Act: 0.9387. Min Act: -0.0001

Data Index: 1245121 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 1.3317. Min Range: -1.3317

Max Act: 0.8948. Min Act: -0.0000

Data Index: 1153613 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 1.3317. Min Range: -1.3317

Max Act: 0.9576. Min Act: -0.0000

Data Index: 1327311 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 1.3317. Min Range: -1.3317

Max Act: 0.9568. Min Act: -0.0001

Data Index: 1292206 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 1.3317. Min Range: -1.3317

Max Act: 0.8955. Min Act: -0.0000

Data Index: 1304167 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 1.3317. Min Range: -1.3317

Max Act: 0.8898. Min Act: -0.0000

Data Index: 1002553 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 1.3317. Min Range: -1.3317

Max Act: 0.9195. Min Act: -0.0000

Data Index: 117842 (C4 (Web Text))

Max Activating Token Index: 217