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

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

Neuron 576 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3486. Min Range: -3.3486

Max Act: 2.5997. Min Act: -0.0001

Data Index: 527568 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 3.3486. Min Range: -3.3486

Max Act: 3.3486. Min Act: -0.0001

Data Index: 1350094 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 3.3486. Min Range: -3.3486

Max Act: 3.3037. Min Act: -0.0001

Data Index: 1034386 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 3.3486. Min Range: -3.3486

Max Act: 2.9148. Min Act: -0.0001

Data Index: 913637 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 3.3486. Min Range: -3.3486

Max Act: 2.7634. Min Act: -0.0001

Data Index: 428655 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 3.3486. Min Range: -3.3486

Max Act: 2.3563. Min Act: -0.0001

Data Index: 260864 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 3.3486. Min Range: -3.3486

Max Act: 2.8853. Min Act: -0.0001

Data Index: 292983 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 3.3486. Min Range: -3.3486

Max Act: 2.6635. Min Act: -0.0001

Data Index: 126343 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 3.3486. Min Range: -3.3486

Max Act: 2.7867. Min Act: -0.0001

Data Index: 121022 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 3.3486. Min Range: -3.3486

Max Act: 2.8879. Min Act: -0.0001

Data Index: 418551 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 3.3486. Min Range: -3.3486

Max Act: 2.6200. Min Act: -0.0001

Data Index: 850540 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 3.3486. Min Range: -3.3486

Max Act: 2.4931. Min Act: -0.0001

Data Index: 584208 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 3.3486. Min Range: -3.3486

Max Act: 2.4699. Min Act: -0.0001

Data Index: 877858 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 3.3486. Min Range: -3.3486

Max Act: 2.5985. Min Act: -0.0001

Data Index: 1056285 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 3.3486. Min Range: -3.3486

Max Act: 2.5261. Min Act: -0.0001

Data Index: 200049 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 3.3486. Min Range: -3.3486

Max Act: 2.7710. Min Act: -0.0001

Data Index: 903618 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 3.3486. Min Range: -3.3486

Max Act: 2.4637. Min Act: -0.0001

Data Index: 444371 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 3.3486. Min Range: -3.3486

Max Act: 2.4523. Min Act: -0.0001

Data Index: 724981 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 3.3486. Min Range: -3.3486

Max Act: 2.4053. Min Act: -0.0001

Data Index: 407104 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 3.3486. Min Range: -3.3486

Max Act: 2.3278. Min Act: -0.0001

Data Index: 914931 (C4 (Web Text))

Max Activating Token Index: 530