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

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

Neuron 3321 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: 6.0228. Min Range: -6.0228

Max Act: 5.8420. Min Act: -0.0000

Data Index: 771376 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 6.0228. Min Range: -6.0228

Max Act: 6.0228. Min Act: -0.0000

Data Index: 732245 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 6.0228. Min Range: -6.0228

Max Act: 5.9203. Min Act: -0.0000

Data Index: 225275 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 6.0228. Min Range: -6.0228

Max Act: 5.5435. Min Act: -0.0000

Data Index: 361984 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 6.0228. Min Range: -6.0228

Max Act: 5.5520. Min Act: -0.0000

Data Index: 934661 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 6.0228. Min Range: -6.0228

Max Act: 5.1648. Min Act: -0.0000

Data Index: 703043 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 6.0228. Min Range: -6.0228

Max Act: 4.9244. Min Act: -0.0000

Data Index: 345790 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 6.0228. Min Range: -6.0228

Max Act: 4.8553. Min Act: -0.0000

Data Index: 200216 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 6.0228. Min Range: -6.0228

Max Act: 4.9346. Min Act: -0.0000

Data Index: 163946 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 6.0228. Min Range: -6.0228

Max Act: 4.8996. Min Act: -0.0000

Data Index: 835936 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 6.0228. Min Range: -6.0228

Max Act: 4.9020. Min Act: -0.0000

Data Index: 92466 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 6.0228. Min Range: -6.0228

Max Act: 4.8795. Min Act: -0.0000

Data Index: 200733 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 6.0228. Min Range: -6.0228

Max Act: 4.7077. Min Act: 0.0000

Data Index: 72858 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 6.0228. Min Range: -6.0228

Max Act: 4.8521. Min Act: -0.0000

Data Index: 543186 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 6.0228. Min Range: -6.0228

Max Act: 4.8354. Min Act: -0.0000

Data Index: 384588 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 6.0228. Min Range: -6.0228

Max Act: 4.8090. Min Act: -0.0000

Data Index: 399167 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 6.0228. Min Range: -6.0228

Max Act: 4.7338. Min Act: -0.0000

Data Index: 788117 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 6.0228. Min Range: -6.0228

Max Act: 4.6824. Min Act: -0.0000

Data Index: 103648 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 6.0228. Min Range: -6.0228

Max Act: 4.8903. Min Act: -0.0000

Data Index: 800743 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 6.0228. Min Range: -6.0228

Max Act: 4.6866. Min Act: -0.0000

Data Index: 1319367 (C4 (Web Text))

Max Activating Token Index: 217