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

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

Neuron 4624 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: 1.5046. Min Range: -1.5046

Max Act: 1.5046. Min Act: -0.0000

Data Index: 355725 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 1.5046. Min Range: -1.5046

Max Act: 1.4297. Min Act: -0.0000

Data Index: 1090394 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 1.5046. Min Range: -1.5046

Max Act: 1.3316. Min Act: -0.0000

Data Index: 777054 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 1.5046. Min Range: -1.5046

Max Act: 1.2203. Min Act: -0.0000

Data Index: 846532 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 1.5046. Min Range: -1.5046

Max Act: 1.1598. Min Act: -0.0000

Data Index: 1295813 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 1.5046. Min Range: -1.5046

Max Act: 1.1673. Min Act: -0.0000

Data Index: 137932 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 1.5046. Min Range: -1.5046

Max Act: 1.1003. Min Act: -0.0000

Data Index: 763159 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 1.5046. Min Range: -1.5046

Max Act: 1.1324. Min Act: -0.0000

Data Index: 21717 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 1.5046. Min Range: -1.5046

Max Act: 0.9532. Min Act: -0.0000

Data Index: 127032 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 1.5046. Min Range: -1.5046

Max Act: 0.9947. Min Act: -0.0000

Data Index: 860388 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 1.5046. Min Range: -1.5046

Max Act: 0.9811. Min Act: -0.0000

Data Index: 289633 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 1.5046. Min Range: -1.5046

Max Act: 0.9581. Min Act: -0.0000

Data Index: 697357 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 1.5046. Min Range: -1.5046

Max Act: 0.9225. Min Act: -0.0000

Data Index: 509799 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 1.5046. Min Range: -1.5046

Max Act: 0.9269. Min Act: -0.0000

Data Index: 1124358 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 1.5046. Min Range: -1.5046

Max Act: 0.9602. Min Act: -0.0000

Data Index: 1044700 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 1.5046. Min Range: -1.5046

Max Act: 0.8289. Min Act: -0.0000

Data Index: 315304 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 1.5046. Min Range: -1.5046

Max Act: 0.8945. Min Act: -0.0000

Data Index: 589106 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 1.5046. Min Range: -1.5046

Max Act: 0.9121. Min Act: -0.0000

Data Index: 1315620 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 1.5046. Min Range: -1.5046

Max Act: 0.9332. Min Act: -0.0000

Data Index: 301183 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 1.5046. Min Range: -1.5046

Max Act: 0.8364. Min Act: -0.0000

Data Index: 789417 (C4 (Web Text))

Max Activating Token Index: 996