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

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

Neuron 2102 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0212. Min Range: -4.0212

Max Act: 3.7533. Min Act: -0.0001

Data Index: 1241236 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 4.0212. Min Range: -4.0212

Max Act: 4.0212. Min Act: -0.0000

Data Index: 533053 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 4.0212. Min Range: -4.0212

Max Act: 3.3502. Min Act: -0.0001

Data Index: 818194 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 4.0212. Min Range: -4.0212

Max Act: 3.0494. Min Act: -0.0001

Data Index: 11376 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 4.0212. Min Range: -4.0212

Max Act: 2.8674. Min Act: -0.0001

Data Index: 230057 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 4.0212. Min Range: -4.0212

Max Act: 3.0085. Min Act: -0.0001

Data Index: 212476 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 4.0212. Min Range: -4.0212

Max Act: 2.9461. Min Act: -0.0000

Data Index: 433502 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 4.0212. Min Range: -4.0212

Max Act: 3.0166. Min Act: -0.0001

Data Index: 211571 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 4.0212. Min Range: -4.0212

Max Act: 2.9670. Min Act: -0.0001

Data Index: 558086 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 4.0212. Min Range: -4.0212

Max Act: 3.1126. Min Act: -0.0001

Data Index: 882793 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 4.0212. Min Range: -4.0212

Max Act: 2.8227. Min Act: -0.0000

Data Index: 54423 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 4.0212. Min Range: -4.0212

Max Act: 2.9269. Min Act: -0.0000

Data Index: 288685 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 4.0212. Min Range: -4.0212

Max Act: 2.7643. Min Act: -0.0001

Data Index: 424282 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 4.0212. Min Range: -4.0212

Max Act: 2.7236. Min Act: -0.0001

Data Index: 261528 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 4.0212. Min Range: -4.0212

Max Act: 2.7090. Min Act: -0.0001

Data Index: 868429 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 4.0212. Min Range: -4.0212

Max Act: 2.5808. Min Act: -0.0000

Data Index: 1359476 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 4.0212. Min Range: -4.0212

Max Act: 2.7466. Min Act: -0.0001

Data Index: 652305 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 4.0212. Min Range: -4.0212

Max Act: 2.7438. Min Act: -0.0000

Data Index: 1163621 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 4.0212. Min Range: -4.0212

Max Act: 2.7079. Min Act: -0.0001

Data Index: 816165 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 4.0212. Min Range: -4.0212

Max Act: 2.5747. Min Act: -0.0001

Data Index: 48215 (C4 (Web Text))

Max Activating Token Index: 617