Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 38 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.4327. Min Act: -0.0002

Data Index: 1208003 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.4157. Min Act: -0.0001

Data Index: 139876 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3853. Min Act: -0.0002

Data Index: 657747 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3778. Min Act: -0.0002

Data Index: 1089880 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3624. Min Act: -0.0001

Data Index: 142507 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3616. Min Act: -0.0002

Data Index: 590116 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3609. Min Act: -0.0002

Data Index: 685611 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3598. Min Act: -0.0002

Data Index: 317626 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3313. Min Act: -0.0002

Data Index: 724804 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3536. Min Act: -0.0002

Data Index: 1341531 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3488. Min Act: -0.0001

Data Index: 773754 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3484. Min Act: -0.0002

Data Index: 1271495 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3585. Min Act: -0.0001

Data Index: 261735 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3434. Min Act: -0.0002

Data Index: 23707 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3479. Min Act: -0.0002

Data Index: 735139 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3204. Min Act: -0.0001

Data Index: 138483 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3303. Min Act: -0.0001

Data Index: 591761 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3313. Min Act: -0.0002

Data Index: 644106 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3261. Min Act: -0.0001

Data Index: 316476 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3291. Min Act: -0.0001

Data Index: 416675 (C4 (Web Text))

Max Activating Token Index: 869