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

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

Neuron 95 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.9590. Min Act: -0.0000

Data Index: 1008513 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.8439. Min Act: -0.0000

Data Index: 145390 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.7761. Min Act: -0.0000

Data Index: 977506 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.7495. Min Act: -0.0000

Data Index: 90572 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.7169. Min Act: -0.0000

Data Index: 161038 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.7141. Min Act: -0.0000

Data Index: 97266 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.6855. Min Act: -0.0000

Data Index: 798327 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.5653. Min Act: -0.0000

Data Index: 1204540 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.6616. Min Act: -0.0000

Data Index: 848157 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.5350. Min Act: -0.0000

Data Index: 560646 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.6044. Min Act: -0.0000

Data Index: 1032098 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.5660. Min Act: -0.0000

Data Index: 594889 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.5431. Min Act: -0.0000

Data Index: 803027 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.6104. Min Act: -0.0000

Data Index: 130875 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.5178. Min Act: -0.0000

Data Index: 1351622 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.5932. Min Act: -0.0000

Data Index: 858624 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.4949. Min Act: -0.0000

Data Index: 649736 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.4194. Min Act: -0.0000

Data Index: 497097 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.4631. Min Act: -0.0000

Data Index: 139432 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 1.9590. Min Range: -1.9590

Max Act: 1.4811. Min Act: -0.0000

Data Index: 320894 (C4 (Web Text))

Max Activating Token Index: 879