Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 246 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3577. Min Range: -1.3577

Max Act: 1.3384. Min Act: -0.0000

Data Index: 42428 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 1.3577. Min Range: -1.3577

Max Act: 1.3577. Min Act: -0.0000

Data Index: 302800 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 1.3577. Min Range: -1.3577

Max Act: 1.2957. Min Act: -0.0000

Data Index: 852654 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 1.3577. Min Range: -1.3577

Max Act: 1.1953. Min Act: -0.0000

Data Index: 997125 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 1.3577. Min Range: -1.3577

Max Act: 1.1650. Min Act: -0.0000

Data Index: 1119752 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 1.3577. Min Range: -1.3577

Max Act: 1.1708. Min Act: -0.0000

Data Index: 391291 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 1.3577. Min Range: -1.3577

Max Act: 1.1677. Min Act: -0.0000

Data Index: 1315758 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 1.3577. Min Range: -1.3577

Max Act: 1.1131. Min Act: -0.0000

Data Index: 214218 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 1.3577. Min Range: -1.3577

Max Act: 1.1000. Min Act: -0.0000

Data Index: 833222 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 1.3577. Min Range: -1.3577

Max Act: 1.0609. Min Act: -0.0000

Data Index: 1325873 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 1.3577. Min Range: -1.3577

Max Act: 1.0769. Min Act: -0.0000

Data Index: 1259989 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 1.3577. Min Range: -1.3577

Max Act: 1.0678. Min Act: -0.0000

Data Index: 516679 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 1.3577. Min Range: -1.3577

Max Act: 1.0033. Min Act: -0.0000

Data Index: 646670 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 1.3577. Min Range: -1.3577

Max Act: 1.0154. Min Act: -0.0000

Data Index: 250132 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 1.3577. Min Range: -1.3577

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1077095 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 1.3577. Min Range: -1.3577

Max Act: 1.0907. Min Act: -0.0000

Data Index: 1198036 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 1.3577. Min Range: -1.3577

Max Act: 1.0178. Min Act: -0.0000

Data Index: 658042 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 1.3577. Min Range: -1.3577

Max Act: 1.0653. Min Act: -0.0000

Data Index: 1132204 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 1.3577. Min Range: -1.3577

Max Act: 0.9979. Min Act: -0.0000

Data Index: 1058035 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 1.3577. Min Range: -1.3577

Max Act: 1.0417. Min Act: -0.0000

Data Index: 917621 (C4 (Web Text))

Max Activating Token Index: 252