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

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

Neuron 189 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.6095. Min Act: -0.0001

Data Index: 151897 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.3589. Min Act: -0.0001

Data Index: 1295743 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.2227. Min Act: -0.0001

Data Index: 1154879 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.1768. Min Act: -0.0001

Data Index: 892429 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.2348. Min Act: -0.0001

Data Index: 739362 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.3014. Min Act: -0.0001

Data Index: 645240 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.2852. Min Act: -0.0001

Data Index: 156124 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.1585. Min Act: -0.0001

Data Index: 376231 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.1608. Min Act: -0.0001

Data Index: 298929 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.1243. Min Act: -0.0001

Data Index: 253785 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.2493. Min Act: -0.0001

Data Index: 92856 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.1800. Min Act: -0.0001

Data Index: 310633 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.1527. Min Act: -0.0001

Data Index: 1187058 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.1132. Min Act: -0.0001

Data Index: 519764 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.0405. Min Act: -0.0001

Data Index: 501078 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.2346. Min Act: -0.0001

Data Index: 1259480 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.0492. Min Act: -0.0001

Data Index: 589585 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.0576. Min Act: -0.0001

Data Index: 162657 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.1031. Min Act: -0.0001

Data Index: 707133 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 1.6095. Min Range: -1.6095

Max Act: 1.0302. Min Act: -0.0001

Data Index: 1245236 (C4 (Web Text))

Max Activating Token Index: 788