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

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

Neuron 3822 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4330. Min Range: -1.4330

Max Act: 1.4055. Min Act: -0.0000

Data Index: 1142178 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 1.4330. Min Range: -1.4330

Max Act: 1.4330. Min Act: -0.0000

Data Index: 415229 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 1.4330. Min Range: -1.4330

Max Act: 1.4153. Min Act: -0.0000

Data Index: 364745 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 1.4330. Min Range: -1.4330

Max Act: 1.3905. Min Act: -0.0000

Data Index: 314686 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 1.4330. Min Range: -1.4330

Max Act: 1.3615. Min Act: -0.0000

Data Index: 59576 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 1.4330. Min Range: -1.4330

Max Act: 1.3442. Min Act: -0.0000

Data Index: 452155 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 1.4330. Min Range: -1.4330

Max Act: 1.2885. Min Act: -0.0000

Data Index: 16815 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 1.4330. Min Range: -1.4330

Max Act: 1.1999. Min Act: -0.0000

Data Index: 867774 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 1.4330. Min Range: -1.4330

Max Act: 1.2393. Min Act: -0.0000

Data Index: 959947 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 1.4330. Min Range: -1.4330

Max Act: 1.1989. Min Act: -0.0000

Data Index: 7442 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 1.4330. Min Range: -1.4330

Max Act: 1.0950. Min Act: -0.0000

Data Index: 877091 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 1.4330. Min Range: -1.4330

Max Act: 1.2044. Min Act: -0.0000

Data Index: 68741 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 1.4330. Min Range: -1.4330

Max Act: 1.0626. Min Act: -0.0000

Data Index: 298546 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 1.4330. Min Range: -1.4330

Max Act: 0.8380. Min Act: -0.0000

Data Index: 905054 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 1.4330. Min Range: -1.4330

Max Act: 0.8468. Min Act: -0.0000

Data Index: 1018576 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 1.4330. Min Range: -1.4330

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1169350 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 1.4330. Min Range: -1.4330

Max Act: 0.7932. Min Act: -0.0000

Data Index: 680074 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 1.4330. Min Range: -1.4330

Max Act: 0.7420. Min Act: -0.0000

Data Index: 771473 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 1.4330. Min Range: -1.4330

Max Act: 0.7372. Min Act: -0.0000

Data Index: 36019 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 1.4330. Min Range: -1.4330

Max Act: 0.7146. Min Act: -0.0000

Data Index: 299499 (C4 (Web Text))

Max Activating Token Index: 111