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

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

Neuron 295 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: 0.5892. Min Range: -0.5892

Max Act: 0.5892. Min Act: -0.0000

Data Index: 54053 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.5508. Min Act: -0.0000

Data Index: 518874 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.5178. Min Act: -0.0000

Data Index: 782820 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1131052 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4959. Min Act: -0.0000

Data Index: 735925 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.5092. Min Act: -0.0000

Data Index: 141000 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4760. Min Act: -0.0000

Data Index: 1350842 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4893. Min Act: -0.0000

Data Index: 997036 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.5022. Min Act: -0.0000

Data Index: 938266 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4646. Min Act: -0.0000

Data Index: 632492 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.5112. Min Act: -0.0000

Data Index: 886771 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4728. Min Act: -0.0000

Data Index: 879906 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4583. Min Act: -0.0000

Data Index: 892048 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4688. Min Act: -0.0000

Data Index: 283478 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1637464 (Python Code)

Max Activating Token Index: 448

Text #15

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4637. Min Act: -0.0000

Data Index: 882194 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4742. Min Act: -0.0000

Data Index: 231504 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4464. Min Act: -0.0000

Data Index: 762452 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4691. Min Act: -0.0000

Data Index: 1033081 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4373. Min Act: -0.0000

Data Index: 667573 (C4 (Web Text))

Max Activating Token Index: 21