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

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

Neuron 3928 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3818. Min Act: -0.0000

Data Index: 76239 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3403. Min Act: -0.0000

Data Index: 472501 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3358. Min Act: -0.0000

Data Index: 517313 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3347. Min Act: -0.0000

Data Index: 358452 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3226. Min Act: -0.0000

Data Index: 702053 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3221. Min Act: -0.0000

Data Index: 583531 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3130. Min Act: -0.0000

Data Index: 852642 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3174. Min Act: -0.0001

Data Index: 605674 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3146. Min Act: -0.0000

Data Index: 221645 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3132. Min Act: -0.0000

Data Index: 194197 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3190. Min Act: -0.0001

Data Index: 995942 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3084. Min Act: -0.0000

Data Index: 1321297 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3083. Min Act: -0.0000

Data Index: 475136 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2944. Min Act: -0.0001

Data Index: 699213 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3096. Min Act: -0.0000

Data Index: 345977 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2890. Min Act: -0.0000

Data Index: 466124 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2933. Min Act: -0.0001

Data Index: 781478 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2849. Min Act: -0.0000

Data Index: 197789 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2820. Min Act: -0.0001

Data Index: 19335 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2895. Min Act: -0.0001

Data Index: 317982 (C4 (Web Text))

Max Activating Token Index: 798