Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4260 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7512. Min Range: -2.7512

Max Act: 2.6315. Min Act: -0.0000

Data Index: 793451 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 2.7512. Min Range: -2.7512

Max Act: 2.7512. Min Act: -0.0000

Data Index: 55403 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 2.7512. Min Range: -2.7512

Max Act: 2.4909. Min Act: -0.0000

Data Index: 422518 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 2.7512. Min Range: -2.7512

Max Act: 2.3606. Min Act: -0.0000

Data Index: 209644 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 2.7512. Min Range: -2.7512

Max Act: 2.2608. Min Act: -0.0000

Data Index: 590086 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 2.7512. Min Range: -2.7512

Max Act: 2.1046. Min Act: -0.0000

Data Index: 1171339 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 2.7512. Min Range: -2.7512

Max Act: 2.1597. Min Act: -0.0000

Data Index: 664803 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 2.7512. Min Range: -2.7512

Max Act: 2.0479. Min Act: -0.0000

Data Index: 380378 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 2.7512. Min Range: -2.7512

Max Act: 2.0073. Min Act: -0.0000

Data Index: 1349194 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 2.7512. Min Range: -2.7512

Max Act: 2.0115. Min Act: -0.0000

Data Index: 537146 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 2.7512. Min Range: -2.7512

Max Act: 2.0755. Min Act: -0.0000

Data Index: 184541 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 2.7512. Min Range: -2.7512

Max Act: 1.7648. Min Act: -0.0000

Data Index: 1121595 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 2.7512. Min Range: -2.7512

Max Act: 1.8318. Min Act: -0.0000

Data Index: 459471 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 2.7512. Min Range: -2.7512

Max Act: 1.9082. Min Act: -0.0000

Data Index: 487654 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 2.7512. Min Range: -2.7512

Max Act: 1.9830. Min Act: -0.0000

Data Index: 925168 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 2.7512. Min Range: -2.7512

Max Act: 1.8461. Min Act: -0.0000

Data Index: 575362 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 2.7512. Min Range: -2.7512

Max Act: 1.9302. Min Act: -0.0000

Data Index: 1229319 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 2.7512. Min Range: -2.7512

Max Act: 1.8487. Min Act: -0.0000

Data Index: 46332 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 2.7512. Min Range: -2.7512

Max Act: 1.9220. Min Act: -0.0000

Data Index: 1331110 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 2.7512. Min Range: -2.7512

Max Act: 1.8098. Min Act: -0.0000

Data Index: 553530 (C4 (Web Text))

Max Activating Token Index: 683