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

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

Neuron 4063 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3308. Min Range: -1.3308

Max Act: 1.3308. Min Act: -0.0000

Data Index: 1341685 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 1.3308. Min Range: -1.3308

Max Act: 1.3285. Min Act: -0.0000

Data Index: 1166900 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 1.3308. Min Range: -1.3308

Max Act: 1.2155. Min Act: -0.0000

Data Index: 1080508 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 1.3308. Min Range: -1.3308

Max Act: 1.2942. Min Act: -0.0000

Data Index: 47468 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 1.3308. Min Range: -1.3308

Max Act: 1.2785. Min Act: -0.0000

Data Index: 588366 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 1.3308. Min Range: -1.3308

Max Act: 1.1292. Min Act: -0.0000

Data Index: 1125033 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 1.3308. Min Range: -1.3308

Max Act: 1.1156. Min Act: -0.0000

Data Index: 1277766 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 1.3308. Min Range: -1.3308

Max Act: 1.1314. Min Act: -0.0000

Data Index: 151624 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 1.3308. Min Range: -1.3308

Max Act: 1.0320. Min Act: -0.0000

Data Index: 280833 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 1.3308. Min Range: -1.3308

Max Act: 1.0658. Min Act: -0.0000

Data Index: 793965 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 1.3308. Min Range: -1.3308

Max Act: 1.0825. Min Act: -0.0000

Data Index: 667016 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 1.3308. Min Range: -1.3308

Max Act: 1.0629. Min Act: -0.0000

Data Index: 749886 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 1.3308. Min Range: -1.3308

Max Act: 1.0618. Min Act: -0.0000

Data Index: 1063630 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 1.3308. Min Range: -1.3308

Max Act: 1.0826. Min Act: -0.0000

Data Index: 1052084 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 1.3308. Min Range: -1.3308

Max Act: 1.0492. Min Act: -0.0000

Data Index: 832627 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 1.3308. Min Range: -1.3308

Max Act: 1.0830. Min Act: -0.0000

Data Index: 1236039 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 1.3308. Min Range: -1.3308

Max Act: 1.0092. Min Act: -0.0000

Data Index: 1072711 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 1.3308. Min Range: -1.3308

Max Act: 1.0469. Min Act: -0.0000

Data Index: 120500 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 1.3308. Min Range: -1.3308

Max Act: 1.0065. Min Act: -0.0000

Data Index: 806033 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 1.3308. Min Range: -1.3308

Max Act: 0.9972. Min Act: -0.0000

Data Index: 947731 (C4 (Web Text))

Max Activating Token Index: 266