Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2947 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0432. Min Range: -1.0432

Max Act: 1.0432. Min Act: -0.0001

Data Index: 1335381 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 1.0432. Min Range: -1.0432

Max Act: 0.9894. Min Act: -0.0001

Data Index: 1008365 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 1.0432. Min Range: -1.0432

Max Act: 0.9916. Min Act: -0.0001

Data Index: 1040638 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 1.0432. Min Range: -1.0432

Max Act: 0.9032. Min Act: -0.0001

Data Index: 827550 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 1.0432. Min Range: -1.0432

Max Act: 0.8151. Min Act: -0.0001

Data Index: 51076 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 1.0432. Min Range: -1.0432

Max Act: 0.8045. Min Act: -0.0001

Data Index: 1041681 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 1.0432. Min Range: -1.0432

Max Act: 0.8024. Min Act: -0.0001

Data Index: 586630 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 1.0432. Min Range: -1.0432

Max Act: 0.8162. Min Act: -0.0001

Data Index: 767869 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 1.0432. Min Range: -1.0432

Max Act: 0.7666. Min Act: -0.0001

Data Index: 487439 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 1.0432. Min Range: -1.0432

Max Act: 0.7535. Min Act: -0.0001

Data Index: 1223271 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 1.0432. Min Range: -1.0432

Max Act: 0.8324. Min Act: -0.0001

Data Index: 745723 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 1.0432. Min Range: -1.0432

Max Act: 0.7968. Min Act: -0.0001

Data Index: 348396 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 1.0432. Min Range: -1.0432

Max Act: 0.7925. Min Act: -0.0001

Data Index: 432358 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 1.0432. Min Range: -1.0432

Max Act: 0.7880. Min Act: -0.0001

Data Index: 1246180 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 1.0432. Min Range: -1.0432

Max Act: 0.7428. Min Act: -0.0001

Data Index: 316315 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 1.0432. Min Range: -1.0432

Max Act: 0.7637. Min Act: -0.0001

Data Index: 495217 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 1.0432. Min Range: -1.0432

Max Act: 0.7555. Min Act: -0.0001

Data Index: 809785 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 1.0432. Min Range: -1.0432

Max Act: 0.7604. Min Act: -0.0001

Data Index: 729322 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 1.0432. Min Range: -1.0432

Max Act: 0.7530. Min Act: -0.0001

Data Index: 135581 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 1.0432. Min Range: -1.0432

Max Act: 0.7252. Min Act: -0.0001

Data Index: 97905 (C4 (Web Text))

Max Activating Token Index: 360