Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3382 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.3375. Min Act: -0.0000

Data Index: 496742 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.3074. Min Act: -0.0000

Data Index: 556823 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.3029. Min Act: -0.0000

Data Index: 1126866 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2776. Min Act: -0.0000

Data Index: 131901 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2970. Min Act: -0.0000

Data Index: 667223 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1063155 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2743. Min Act: -0.0000

Data Index: 1240288 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2760. Min Act: -0.0000

Data Index: 728214 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2832. Min Act: -0.0000

Data Index: 173268 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2839. Min Act: -0.0000

Data Index: 406299 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2817. Min Act: -0.0000

Data Index: 181618 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2817. Min Act: -0.0000

Data Index: 347430 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1022491 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2685. Min Act: -0.0000

Data Index: 82289 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2602. Min Act: -0.0000

Data Index: 720476 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2789. Min Act: -0.0000

Data Index: 533843 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2689. Min Act: -0.0000

Data Index: 889591 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2698. Min Act: -0.0000

Data Index: 1318403 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2661. Min Act: -0.0000

Data Index: 75695 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2660. Min Act: -0.0000

Data Index: 6798 (C4 (Web Text))

Max Activating Token Index: 471