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

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

Neuron 383 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2178. Min Range: -4.2178

Max Act: 4.2178. Min Act: -0.0000

Data Index: 101991 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 4.2178. Min Range: -4.2178

Max Act: 3.2717. Min Act: -0.0000

Data Index: 1173784 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 4.2178. Min Range: -4.2178

Max Act: 2.7854. Min Act: -0.0000

Data Index: 220710 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 4.2178. Min Range: -4.2178

Max Act: 2.6651. Min Act: -0.0000

Data Index: 704366 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 4.2178. Min Range: -4.2178

Max Act: 2.4504. Min Act: -0.0000

Data Index: 437801 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 4.2178. Min Range: -4.2178

Max Act: 2.6722. Min Act: -0.0000

Data Index: 365782 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 4.2178. Min Range: -4.2178

Max Act: 2.6899. Min Act: -0.0000

Data Index: 165461 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 4.2178. Min Range: -4.2178

Max Act: 2.6399. Min Act: -0.0000

Data Index: 263534 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 4.2178. Min Range: -4.2178

Max Act: 2.6462. Min Act: -0.0000

Data Index: 74654 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 4.2178. Min Range: -4.2178

Max Act: 2.5252. Min Act: -0.0000

Data Index: 217893 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 4.2178. Min Range: -4.2178

Max Act: 2.8700. Min Act: -0.0000

Data Index: 1111327 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 4.2178. Min Range: -4.2178

Max Act: 2.1325. Min Act: -0.0000

Data Index: 267390 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 4.2178. Min Range: -4.2178

Max Act: 2.4891. Min Act: -0.0000

Data Index: 65569 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 4.2178. Min Range: -4.2178

Max Act: 2.8138. Min Act: -0.0000

Data Index: 348489 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 4.2178. Min Range: -4.2178

Max Act: 2.4336. Min Act: -0.0000

Data Index: 1071573 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 4.2178. Min Range: -4.2178

Max Act: 1.9615. Min Act: -0.0000

Data Index: 380902 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 4.2178. Min Range: -4.2178

Max Act: 2.2643. Min Act: -0.0000

Data Index: 210066 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 4.2178. Min Range: -4.2178

Max Act: 2.3548. Min Act: -0.0000

Data Index: 415045 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 4.2178. Min Range: -4.2178

Max Act: 2.2303. Min Act: -0.0000

Data Index: 1031573 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 4.2178. Min Range: -4.2178

Max Act: 2.4804. Min Act: -0.0000

Data Index: 107933 (C4 (Web Text))

Max Activating Token Index: 279