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

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

Neuron 2412 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4069. Min Range: -2.4069

Max Act: 2.4069. Min Act: -0.0000

Data Index: 550723 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 2.4069. Min Range: -2.4069

Max Act: 1.8629. Min Act: -0.0000

Data Index: 1113112 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 2.4069. Min Range: -2.4069

Max Act: 1.5585. Min Act: -0.0000

Data Index: 957551 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 2.4069. Min Range: -2.4069

Max Act: 1.5074. Min Act: -0.0000

Data Index: 752588 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 2.4069. Min Range: -2.4069

Max Act: 1.4505. Min Act: -0.0000

Data Index: 871562 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 2.4069. Min Range: -2.4069

Max Act: 1.5123. Min Act: -0.0000

Data Index: 65944 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 2.4069. Min Range: -2.4069

Max Act: 1.3856. Min Act: -0.0000

Data Index: 10781 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 2.4069. Min Range: -2.4069

Max Act: 1.3805. Min Act: -0.0000

Data Index: 1319627 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 2.4069. Min Range: -2.4069

Max Act: 1.3911. Min Act: -0.0000

Data Index: 608791 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 2.4069. Min Range: -2.4069

Max Act: 1.3160. Min Act: -0.0000

Data Index: 998991 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 2.4069. Min Range: -2.4069

Max Act: 1.3044. Min Act: -0.0000

Data Index: 235717 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 2.4069. Min Range: -2.4069

Max Act: 1.1844. Min Act: -0.0000

Data Index: 444587 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 2.4069. Min Range: -2.4069

Max Act: 1.0935. Min Act: -0.0000

Data Index: 77237 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 2.4069. Min Range: -2.4069

Max Act: 1.1579. Min Act: -0.0000

Data Index: 1199609 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 2.4069. Min Range: -2.4069

Max Act: 1.1157. Min Act: -0.0000

Data Index: 779937 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 2.4069. Min Range: -2.4069

Max Act: 1.1416. Min Act: -0.0000

Data Index: 880349 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 2.4069. Min Range: -2.4069

Max Act: 1.0252. Min Act: -0.0000

Data Index: 948985 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 2.4069. Min Range: -2.4069

Max Act: 1.1541. Min Act: -0.0000

Data Index: 222613 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 2.4069. Min Range: -2.4069

Max Act: 1.1173. Min Act: -0.0000

Data Index: 307672 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 2.4069. Min Range: -2.4069

Max Act: 1.0596. Min Act: -0.0000

Data Index: 949033 (C4 (Web Text))

Max Activating Token Index: 454