Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 677 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6515. Min Range: -2.6515

Max Act: 2.6515. Min Act: -0.0001

Data Index: 165310 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 2.6515. Min Range: -2.6515

Max Act: 2.5257. Min Act: -0.0000

Data Index: 571087 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 2.6515. Min Range: -2.6515

Max Act: 1.4858. Min Act: -0.0000

Data Index: 1139486 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 2.6515. Min Range: -2.6515

Max Act: 1.4922. Min Act: -0.0000

Data Index: 1224062 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 2.6515. Min Range: -2.6515

Max Act: 1.3564. Min Act: -0.0000

Data Index: 750896 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 2.6515. Min Range: -2.6515

Max Act: 1.4150. Min Act: -0.0000

Data Index: 764205 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 2.6515. Min Range: -2.6515

Max Act: 1.2981. Min Act: -0.0000

Data Index: 1250544 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 2.6515. Min Range: -2.6515

Max Act: 1.2804. Min Act: -0.0000

Data Index: 435625 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 2.6515. Min Range: -2.6515

Max Act: 1.3888. Min Act: -0.0000

Data Index: 972044 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 2.6515. Min Range: -2.6515

Max Act: 1.2825. Min Act: -0.0000

Data Index: 488436 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 2.6515. Min Range: -2.6515

Max Act: 1.3220. Min Act: -0.0000

Data Index: 511033 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 2.6515. Min Range: -2.6515

Max Act: 1.1619. Min Act: -0.0000

Data Index: 435996 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 2.6515. Min Range: -2.6515

Max Act: 1.1541. Min Act: -0.0000

Data Index: 1119499 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 2.6515. Min Range: -2.6515

Max Act: 1.2551. Min Act: -0.0000

Data Index: 350909 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 2.6515. Min Range: -2.6515

Max Act: 1.2045. Min Act: -0.0000

Data Index: 1287143 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 2.6515. Min Range: -2.6515

Max Act: 1.2078. Min Act: -0.0000

Data Index: 1038382 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 2.6515. Min Range: -2.6515

Max Act: 1.2249. Min Act: -0.0001

Data Index: 1076161 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 2.6515. Min Range: -2.6515

Max Act: 1.0923. Min Act: -0.0000

Data Index: 1273232 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 2.6515. Min Range: -2.6515

Max Act: 1.1268. Min Act: -0.0000

Data Index: 1223271 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 2.6515. Min Range: -2.6515

Max Act: 1.1468. Min Act: -0.0001

Data Index: 533683 (C4 (Web Text))

Max Activating Token Index: 315