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

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

Neuron 4418 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7575. Min Range: -2.7575

Max Act: 2.3891. Min Act: -0.0000

Data Index: 469580 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 2.7575. Min Range: -2.7575

Max Act: 2.7575. Min Act: -0.0000

Data Index: 844063 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 2.7575. Min Range: -2.7575

Max Act: 2.4036. Min Act: -0.0000

Data Index: 1322111 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 2.7575. Min Range: -2.7575

Max Act: 2.1968. Min Act: -0.0000

Data Index: 891160 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 2.7575. Min Range: -2.7575

Max Act: 1.9441. Min Act: -0.0000

Data Index: 1185293 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 2.7575. Min Range: -2.7575

Max Act: 1.8880. Min Act: -0.0000

Data Index: 1069691 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 2.7575. Min Range: -2.7575

Max Act: 2.0005. Min Act: -0.0000

Data Index: 220870 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 2.7575. Min Range: -2.7575

Max Act: 2.0595. Min Act: -0.0000

Data Index: 136766 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 2.7575. Min Range: -2.7575

Max Act: 2.0188. Min Act: -0.0000

Data Index: 1028344 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 2.7575. Min Range: -2.7575

Max Act: 1.9129. Min Act: -0.0000

Data Index: 320847 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 2.7575. Min Range: -2.7575

Max Act: 1.7865. Min Act: -0.0000

Data Index: 188232 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 2.7575. Min Range: -2.7575

Max Act: 1.9701. Min Act: -0.0000

Data Index: 204897 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 2.7575. Min Range: -2.7575

Max Act: 1.8394. Min Act: -0.0000

Data Index: 982839 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 2.7575. Min Range: -2.7575

Max Act: 1.8297. Min Act: -0.0000

Data Index: 848551 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 2.7575. Min Range: -2.7575

Max Act: 1.6504. Min Act: -0.0000

Data Index: 619230 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 2.7575. Min Range: -2.7575

Max Act: 2.0246. Min Act: -0.0000

Data Index: 688726 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 2.7575. Min Range: -2.7575

Max Act: 1.8046. Min Act: -0.0000

Data Index: 378318 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 2.7575. Min Range: -2.7575

Max Act: 1.7894. Min Act: -0.0000

Data Index: 1170059 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 2.7575. Min Range: -2.7575

Max Act: 1.7909. Min Act: -0.0000

Data Index: 985103 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 2.7575. Min Range: -2.7575

Max Act: 1.8932. Min Act: -0.0000

Data Index: 749842 (C4 (Web Text))

Max Activating Token Index: 1016