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

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

Neuron 3526 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: 1.5679. Min Range: -1.5679

Max Act: 1.5679. Min Act: -0.0000

Data Index: 291464 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 1.5679. Min Range: -1.5679

Max Act: 1.3382. Min Act: -0.0000

Data Index: 1352910 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 1.5679. Min Range: -1.5679

Max Act: 1.2420. Min Act: -0.0000

Data Index: 1161384 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 1.5679. Min Range: -1.5679

Max Act: 1.2358. Min Act: -0.0000

Data Index: 451385 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 1.5679. Min Range: -1.5679

Max Act: 1.2193. Min Act: -0.0000

Data Index: 389286 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 1.5679. Min Range: -1.5679

Max Act: 1.0910. Min Act: -0.0000

Data Index: 133481 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 1.5679. Min Range: -1.5679

Max Act: 1.1096. Min Act: -0.0000

Data Index: 1143788 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 1.5679. Min Range: -1.5679

Max Act: 1.0753. Min Act: -0.0000

Data Index: 820303 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 1.5679. Min Range: -1.5679

Max Act: 1.0014. Min Act: -0.0000

Data Index: 547471 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 1.5679. Min Range: -1.5679

Max Act: 1.0496. Min Act: -0.0000

Data Index: 4618 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 1.5679. Min Range: -1.5679

Max Act: 1.0689. Min Act: -0.0000

Data Index: 1171176 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 1.5679. Min Range: -1.5679

Max Act: 1.0071. Min Act: -0.0000

Data Index: 498815 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 1.5679. Min Range: -1.5679

Max Act: 1.0318. Min Act: -0.0000

Data Index: 1577758 (Python Code)

Max Activating Token Index: 675

Text #13

Max Range: 1.5679. Min Range: -1.5679

Max Act: 0.9971. Min Act: -0.0000

Data Index: 1036987 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 1.5679. Min Range: -1.5679

Max Act: 1.0044. Min Act: -0.0000

Data Index: 269092 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 1.5679. Min Range: -1.5679

Max Act: 0.9563. Min Act: -0.0000

Data Index: 284083 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 1.5679. Min Range: -1.5679

Max Act: 0.9313. Min Act: -0.0000

Data Index: 26473 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 1.5679. Min Range: -1.5679

Max Act: 0.9348. Min Act: -0.0000

Data Index: 1211111 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 1.5679. Min Range: -1.5679

Max Act: 0.9624. Min Act: -0.0000

Data Index: 583977 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 1.5679. Min Range: -1.5679

Max Act: 0.9298. Min Act: -0.0000

Data Index: 556899 (C4 (Web Text))

Max Activating Token Index: 213