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

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

Neuron 5337 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4618. Min Range: -2.4618

Max Act: 2.4618. Min Act: -0.0000

Data Index: 580712 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 2.4618. Min Range: -2.4618

Max Act: 2.4135. Min Act: -0.0000

Data Index: 382337 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 2.4618. Min Range: -2.4618

Max Act: 2.4073. Min Act: -0.0000

Data Index: 772106 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 2.4618. Min Range: -2.4618

Max Act: 2.2351. Min Act: -0.0000

Data Index: 1128288 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 2.4618. Min Range: -2.4618

Max Act: 2.2373. Min Act: -0.0000

Data Index: 485154 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 2.4618. Min Range: -2.4618

Max Act: 2.3045. Min Act: -0.0000

Data Index: 1130363 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 2.4618. Min Range: -2.4618

Max Act: 2.1795. Min Act: -0.0000

Data Index: 1282389 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 2.4618. Min Range: -2.4618

Max Act: 2.0194. Min Act: -0.0000

Data Index: 151465 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 2.4618. Min Range: -2.4618

Max Act: 1.8598. Min Act: -0.0000

Data Index: 823241 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 2.4618. Min Range: -2.4618

Max Act: 1.9336. Min Act: -0.0000

Data Index: 119908 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 2.4618. Min Range: -2.4618

Max Act: 2.1133. Min Act: -0.0000

Data Index: 648752 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 2.4618. Min Range: -2.4618

Max Act: 1.9905. Min Act: -0.0000

Data Index: 167510 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 2.4618. Min Range: -2.4618

Max Act: 2.0267. Min Act: -0.0000

Data Index: 553432 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 2.4618. Min Range: -2.4618

Max Act: 1.8107. Min Act: -0.0000

Data Index: 828624 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 2.4618. Min Range: -2.4618

Max Act: 1.8990. Min Act: -0.0000

Data Index: 176103 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 2.4618. Min Range: -2.4618

Max Act: 1.6485. Min Act: -0.0000

Data Index: 489809 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 2.4618. Min Range: -2.4618

Max Act: 1.6116. Min Act: -0.0000

Data Index: 246109 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 2.4618. Min Range: -2.4618

Max Act: 1.6945. Min Act: -0.0000

Data Index: 690123 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 2.4618. Min Range: -2.4618

Max Act: 1.7302. Min Act: -0.0000

Data Index: 1201397 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 2.4618. Min Range: -2.4618

Max Act: 1.4672. Min Act: -0.0000

Data Index: 386687 (C4 (Web Text))

Max Activating Token Index: 218