Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3059 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1300. Min Range: -1.1300

Max Act: 1.0766. Min Act: -0.0004

Data Index: 296876 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 1.1300. Min Range: -1.1300

Max Act: 0.6688. Min Act: -0.0004

Data Index: 1181496 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 1.1300. Min Range: -1.1300

Max Act: 0.9162. Min Act: -0.0004

Data Index: 144689 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 1.1300. Min Range: -1.1300

Max Act: 0.8871. Min Act: -0.0004

Data Index: 745835 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 1.1300. Min Range: -1.1300

Max Act: 1.1300. Min Act: -0.0004

Data Index: 956118 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 1.1300. Min Range: -1.1300

Max Act: 0.9637. Min Act: -0.0004

Data Index: 561511 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 1.1300. Min Range: -1.1300

Max Act: 0.8537. Min Act: -0.0004

Data Index: 378618 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 1.1300. Min Range: -1.1300

Max Act: 0.8712. Min Act: -0.0004

Data Index: 1065441 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 1.1300. Min Range: -1.1300

Max Act: 0.8685. Min Act: -0.0004

Data Index: 154540 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 1.1300. Min Range: -1.1300

Max Act: 1.0338. Min Act: -0.0004

Data Index: 1022754 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 1.1300. Min Range: -1.1300

Max Act: 0.9070. Min Act: -0.0004

Data Index: 1057316 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 1.1300. Min Range: -1.1300

Max Act: 0.8055. Min Act: -0.0004

Data Index: 1069433 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 1.1300. Min Range: -1.1300

Max Act: 0.8771. Min Act: -0.0004

Data Index: 939393 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 1.1300. Min Range: -1.1300

Max Act: 0.8491. Min Act: -0.0004

Data Index: 88390 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 1.1300. Min Range: -1.1300

Max Act: 0.8009. Min Act: -0.0004

Data Index: 314979 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 1.1300. Min Range: -1.1300

Max Act: 1.0403. Min Act: -0.0004

Data Index: 817866 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 1.1300. Min Range: -1.1300

Max Act: 0.8974. Min Act: -0.0004

Data Index: 873804 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 1.1300. Min Range: -1.1300

Max Act: 0.8456. Min Act: -0.0004

Data Index: 915370 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 1.1300. Min Range: -1.1300

Max Act: 0.9461. Min Act: -0.0004

Data Index: 629796 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 1.1300. Min Range: -1.1300

Max Act: 0.8405. Min Act: -0.0004

Data Index: 754006 (C4 (Web Text))

Max Activating Token Index: 512