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

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

Neuron 3256 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: 1.4034. Min Range: -1.4034

Max Act: 1.4013. Min Act: -0.0000

Data Index: 324086 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.3775. Min Act: -0.0000

Data Index: 384663 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.4034. Min Act: -0.0000

Data Index: 576614 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.3211. Min Act: -0.0000

Data Index: 812489 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.2475. Min Act: -0.0000

Data Index: 901271 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.2678. Min Act: -0.0000

Data Index: 926642 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.1784. Min Act: -0.0000

Data Index: 879946 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.2269. Min Act: -0.0000

Data Index: 1508029 (Python Code)

Max Activating Token Index: 912

Text #8

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.1081. Min Act: -0.0000

Data Index: 641246 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.0247. Min Act: -0.0000

Data Index: 490516 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.0714. Min Act: -0.0000

Data Index: 167794 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.0196. Min Act: -0.0000

Data Index: 1620821 (Python Code)

Max Activating Token Index: 422

Text #12

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.0750. Min Act: -0.0000

Data Index: 289092 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.0874. Min Act: -0.0000

Data Index: 1002619 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.2444. Min Act: -0.0000

Data Index: 881471 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 1.4034. Min Range: -1.4034

Max Act: 1.0589. Min Act: -0.0000

Data Index: 349104 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.9505. Min Act: -0.0000

Data Index: 1403156 (Python Code)

Max Activating Token Index: 592

Text #17

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.9937. Min Act: -0.0000

Data Index: 782243 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.9769. Min Act: -0.0000

Data Index: 57814 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 1.4034. Min Range: -1.4034

Max Act: 0.9569. Min Act: -0.0000

Data Index: 572280 (C4 (Web Text))

Max Activating Token Index: 851