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

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

Neuron 4379 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2487. Min Act: -0.0001

Data Index: 852104 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2552. Min Act: -0.0001

Data Index: 544038 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2540. Min Act: -0.0001

Data Index: 854716 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2313. Min Act: -0.0001

Data Index: 871106 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2249. Min Act: -0.0001

Data Index: 18140 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2639. Min Act: -0.0001

Data Index: 1160254 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2475. Min Act: -0.0001

Data Index: 901488 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2449. Min Act: -0.0001

Data Index: 1103072 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2291. Min Act: -0.0001

Data Index: 1223473 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2398. Min Act: -0.0001

Data Index: 651282 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2147. Min Act: -0.0001

Data Index: 128999 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2111. Min Act: -0.0001

Data Index: 882474 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1995. Min Act: -0.0001

Data Index: 225966 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2203. Min Act: -0.0001

Data Index: 423301 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2103. Min Act: -0.0001

Data Index: 852662 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2255. Min Act: -0.0001

Data Index: 1219083 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2139. Min Act: -0.0001

Data Index: 7186 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2151. Min Act: -0.0001

Data Index: 360350 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2189. Min Act: -0.0001

Data Index: 839249 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2029. Min Act: -0.0001

Data Index: 771878 (C4 (Web Text))

Max Activating Token Index: 517