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

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

Neuron 3925 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.3035. Min Act: -0.0000

Data Index: 830656 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2760. Min Act: -0.0000

Data Index: 242355 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2718. Min Act: -0.0000

Data Index: 561687 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2780. Min Act: -0.0000

Data Index: 587473 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2699. Min Act: -0.0000

Data Index: 788095 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2654. Min Act: -0.0000

Data Index: 1258167 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2638. Min Act: -0.0000

Data Index: 1168146 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2691. Min Act: -0.0000

Data Index: 608506 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2699. Min Act: -0.0000

Data Index: 446908 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2663. Min Act: -0.0000

Data Index: 461720 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2568. Min Act: -0.0000

Data Index: 380670 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2652. Min Act: -0.0000

Data Index: 787489 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2739. Min Act: -0.0000

Data Index: 779421 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2538. Min Act: -0.0000

Data Index: 62281 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2727. Min Act: -0.0000

Data Index: 969261 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2518. Min Act: -0.0000

Data Index: 938818 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2585. Min Act: -0.0000

Data Index: 492649 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2382. Min Act: -0.0000

Data Index: 27655 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2464. Min Act: -0.0000

Data Index: 442101 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2447. Min Act: -0.0000

Data Index: 841547 (C4 (Web Text))

Max Activating Token Index: 563