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

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

Neuron 2157 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5902. Min Range: -2.5902

Max Act: 2.5902. Min Act: -0.0000

Data Index: 56948 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 2.5902. Min Range: -2.5902

Max Act: 2.1034. Min Act: -0.0000

Data Index: 523305 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 2.5902. Min Range: -2.5902

Max Act: 2.3116. Min Act: -0.0000

Data Index: 1052316 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 2.5902. Min Range: -2.5902

Max Act: 2.3037. Min Act: -0.0000

Data Index: 569910 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 2.5902. Min Range: -2.5902

Max Act: 2.0637. Min Act: -0.0000

Data Index: 795276 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 2.5902. Min Range: -2.5902

Max Act: 2.2669. Min Act: -0.0000

Data Index: 53329 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 2.5902. Min Range: -2.5902

Max Act: 2.1476. Min Act: -0.0000

Data Index: 1103364 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 2.5902. Min Range: -2.5902

Max Act: 2.0208. Min Act: -0.0000

Data Index: 591792 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 2.5902. Min Range: -2.5902

Max Act: 2.1463. Min Act: -0.0000

Data Index: 1222064 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 2.5902. Min Range: -2.5902

Max Act: 2.2251. Min Act: -0.0000

Data Index: 160407 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 2.5902. Min Range: -2.5902

Max Act: 2.0889. Min Act: -0.0000

Data Index: 863607 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 2.5902. Min Range: -2.5902

Max Act: 2.1996. Min Act: 0.0000

Data Index: 1013711 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 2.5902. Min Range: -2.5902

Max Act: 2.0482. Min Act: -0.0000

Data Index: 702106 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 2.5902. Min Range: -2.5902

Max Act: 2.0365. Min Act: 0.0000

Data Index: 1265653 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 2.5902. Min Range: -2.5902

Max Act: 2.0408. Min Act: -0.0000

Data Index: 208182 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 2.5902. Min Range: -2.5902

Max Act: 2.0163. Min Act: -0.0000

Data Index: 1189256 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 2.5902. Min Range: -2.5902

Max Act: 2.0998. Min Act: -0.0000

Data Index: 213012 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 2.5902. Min Range: -2.5902

Max Act: 1.8651. Min Act: -0.0000

Data Index: 1194751 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 2.5902. Min Range: -2.5902

Max Act: 1.9807. Min Act: -0.0000

Data Index: 380616 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 2.5902. Min Range: -2.5902

Max Act: 1.9226. Min Act: -0.0000

Data Index: 445943 (C4 (Web Text))

Max Activating Token Index: 515