Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4753 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3545. Min Act: -0.0001

Data Index: 767618 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3674. Min Act: -0.0001

Data Index: 157919 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3382. Min Act: -0.0001

Data Index: 615778 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3639. Min Act: -0.0001

Data Index: 801249 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3506. Min Act: -0.0001

Data Index: 49495 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3412. Min Act: -0.0001

Data Index: 337616 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3264. Min Act: -0.0001

Data Index: 1238062 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2965. Min Act: -0.0001

Data Index: 537700 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.3192. Min Act: -0.0001

Data Index: 859710 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2812. Min Act: -0.0001

Data Index: 563131 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2899. Min Act: -0.0001

Data Index: 163582 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2820. Min Act: -0.0001

Data Index: 42983 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2881. Min Act: -0.0001

Data Index: 626942 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2924. Min Act: -0.0001

Data Index: 1301669 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2913. Min Act: -0.0001

Data Index: 143143 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2723. Min Act: -0.0001

Data Index: 1194898 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2797. Min Act: -0.0001

Data Index: 144333 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2564. Min Act: -0.0001

Data Index: 481230 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2541. Min Act: -0.0001

Data Index: 629376 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.3674. Min Range: -0.3674

Max Act: 0.2624. Min Act: -0.0001

Data Index: 968039 (C4 (Web Text))

Max Activating Token Index: 466