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

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

Neuron 3279 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7258. Min Range: -1.7258

Max Act: 1.7258. Min Act: -0.0000

Data Index: 998231 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 1.7258. Min Range: -1.7258

Max Act: 1.3210. Min Act: -0.0000

Data Index: 1076258 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 1.7258. Min Range: -1.7258

Max Act: 1.0980. Min Act: -0.0000

Data Index: 1104104 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 1.7258. Min Range: -1.7258

Max Act: 1.0194. Min Act: -0.0000

Data Index: 698934 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 1.7258. Min Range: -1.7258

Max Act: 1.1364. Min Act: -0.0000

Data Index: 855759 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 1.7258. Min Range: -1.7258

Max Act: 1.0296. Min Act: -0.0000

Data Index: 664174 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 1.7258. Min Range: -1.7258

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1269282 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 1.7258. Min Range: -1.7258

Max Act: 0.9549. Min Act: -0.0000

Data Index: 82576 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 1.7258. Min Range: -1.7258

Max Act: 0.9060. Min Act: -0.0000

Data Index: 65518 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 1.7258. Min Range: -1.7258

Max Act: 0.8219. Min Act: -0.0000

Data Index: 876421 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 1.7258. Min Range: -1.7258

Max Act: 0.8285. Min Act: -0.0000

Data Index: 427343 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 1.7258. Min Range: -1.7258

Max Act: 0.8401. Min Act: -0.0000

Data Index: 205662 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 1.7258. Min Range: -1.7258

Max Act: 0.7876. Min Act: -0.0000

Data Index: 162536 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 1.7258. Min Range: -1.7258

Max Act: 0.8304. Min Act: -0.0000

Data Index: 143567 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 1.7258. Min Range: -1.7258

Max Act: 0.7714. Min Act: -0.0000

Data Index: 230280 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 1.7258. Min Range: -1.7258

Max Act: 0.8049. Min Act: -0.0000

Data Index: 279414 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 1.7258. Min Range: -1.7258

Max Act: 0.8689. Min Act: -0.0000

Data Index: 972291 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 1.7258. Min Range: -1.7258

Max Act: 0.7772. Min Act: -0.0000

Data Index: 455942 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 1.7258. Min Range: -1.7258

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1162322 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 1.7258. Min Range: -1.7258

Max Act: 0.7884. Min Act: -0.0000

Data Index: 662581 (C4 (Web Text))

Max Activating Token Index: 518