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

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

Neuron 2439 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.8714. Min Act: -0.0000

Data Index: 733240 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.7264. Min Act: -0.0001

Data Index: 315144 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.5558. Min Act: -0.0000

Data Index: 227467 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.5873. Min Act: -0.0001

Data Index: 762225 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.4570. Min Act: -0.0001

Data Index: 985641 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.4598. Min Act: -0.0001

Data Index: 305850 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.4521. Min Act: -0.0001

Data Index: 367325 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.3814. Min Act: -0.0000

Data Index: 335301 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.3175. Min Act: -0.0001

Data Index: 872475 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.3662. Min Act: -0.0000

Data Index: 287616 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.3428. Min Act: -0.0000

Data Index: 533124 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.3321. Min Act: -0.0001

Data Index: 1178798 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.3646. Min Act: -0.0001

Data Index: 993285 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.2803. Min Act: -0.0001

Data Index: 926547 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.2797. Min Act: -0.0001

Data Index: 630630 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.2791. Min Act: -0.0000

Data Index: 65945 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.2807. Min Act: -0.0001

Data Index: 422075 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.2730. Min Act: -0.0000

Data Index: 668428 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.3069. Min Act: -0.0000

Data Index: 1218103 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 1.8714. Min Range: -1.8714

Max Act: 1.2530. Min Act: -0.0000

Data Index: 1105971 (C4 (Web Text))

Max Activating Token Index: 362