Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4953 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.7962. Min Act: -0.0001

Data Index: 200415 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.7268. Min Act: -0.0001

Data Index: 98965 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.6697. Min Act: -0.0001

Data Index: 1290722 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.6628. Min Act: -0.0001

Data Index: 687841 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5539. Min Act: -0.0001

Data Index: 1106256 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5716. Min Act: -0.0001

Data Index: 335542 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5634. Min Act: -0.0001

Data Index: 260827 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5293. Min Act: -0.0001

Data Index: 1298137 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5543. Min Act: -0.0001

Data Index: 182388 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5315. Min Act: -0.0001

Data Index: 1177982 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5306. Min Act: -0.0001

Data Index: 421087 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5537. Min Act: -0.0001

Data Index: 1125814 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.4994. Min Act: -0.0001

Data Index: 730576 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5176. Min Act: -0.0001

Data Index: 420643 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5036. Min Act: -0.0001

Data Index: 465124 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5189. Min Act: -0.0001

Data Index: 761640 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5088. Min Act: -0.0001

Data Index: 185151 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5014. Min Act: -0.0001

Data Index: 818090 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.4810. Min Act: -0.0001

Data Index: 435865 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.4809. Min Act: -0.0001

Data Index: 628952 (C4 (Web Text))

Max Activating Token Index: 688