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

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

Neuron 996 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: 0.3734. Min Range: -0.3734

Max Act: 0.3734. Min Act: -0.0000

Data Index: 436855 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3498. Min Act: -0.0000

Data Index: 939632 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3395. Min Act: -0.0000

Data Index: 974458 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3236. Min Act: -0.0000

Data Index: 377151 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3224. Min Act: -0.0000

Data Index: 1073439 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1212828 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3056. Min Act: -0.0000

Data Index: 5678 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2893. Min Act: -0.0000

Data Index: 949158 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2680. Min Act: -0.0000

Data Index: 337807 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2902. Min Act: -0.0000

Data Index: 568507 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2898. Min Act: -0.0000

Data Index: 363040 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2585. Min Act: -0.0000

Data Index: 942397 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2754. Min Act: -0.0000

Data Index: 69194 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2831. Min Act: -0.0000

Data Index: 403379 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2719. Min Act: -0.0000

Data Index: 912946 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1004490 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2568. Min Act: -0.0000

Data Index: 514465 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2557. Min Act: -0.0000

Data Index: 950175 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2545. Min Act: -0.0000

Data Index: 738480 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1019773 (C4 (Web Text))

Max Activating Token Index: 390