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

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

Neuron 4802 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3870. Min Act: -0.0000

Data Index: 831175 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3573. Min Act: -0.0000

Data Index: 272540 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3267. Min Act: -0.0000

Data Index: 1136608 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3498. Min Act: -0.0000

Data Index: 1077475 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3217. Min Act: -0.0000

Data Index: 578900 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3174. Min Act: -0.0000

Data Index: 399841 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2931. Min Act: -0.0000

Data Index: 803006 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2902. Min Act: -0.0001

Data Index: 1353300 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2934. Min Act: -0.0000

Data Index: 1299811 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.3076. Min Act: -0.0000

Data Index: 754168 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2881. Min Act: -0.0000

Data Index: 703734 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2888. Min Act: -0.0001

Data Index: 164653 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2796. Min Act: -0.0001

Data Index: 849707 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2438. Min Act: -0.0001

Data Index: 933947 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2503. Min Act: -0.0000

Data Index: 1422762 (Python Code)

Max Activating Token Index: 670

Text #15

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2341. Min Act: -0.0000

Data Index: 747740 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2159. Min Act: -0.0001

Data Index: 1246208 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2708. Min Act: -0.0000

Data Index: 1287934 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2295. Min Act: -0.0000

Data Index: 1560569 (Python Code)

Max Activating Token Index: 917

Text #19

Max Range: 0.3870. Min Range: -0.3870

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1258070 (C4 (Web Text))

Max Activating Token Index: 764