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

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

Neuron 145 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: 1.0146. Min Range: -1.0146

Max Act: 1.0146. Min Act: -0.0001

Data Index: 860156 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.9638. Min Act: -0.0001

Data Index: 241321 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.9098. Min Act: -0.0001

Data Index: 582419 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.8453. Min Act: -0.0001

Data Index: 1094893 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.8619. Min Act: -0.0001

Data Index: 34350 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.8178. Min Act: -0.0001

Data Index: 148667 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.9086. Min Act: -0.0001

Data Index: 534917 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7773. Min Act: -0.0001

Data Index: 68182 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7744. Min Act: -0.0001

Data Index: 1196890 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7456. Min Act: -0.0001

Data Index: 1267953 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7640. Min Act: -0.0001

Data Index: 936056 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7928. Min Act: -0.0001

Data Index: 925493 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7486. Min Act: -0.0001

Data Index: 707681 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7426. Min Act: -0.0001

Data Index: 385657 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7305. Min Act: -0.0001

Data Index: 1608796 (Python Code)

Max Activating Token Index: 920

Text #15

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7406. Min Act: -0.0001

Data Index: 218133 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7833. Min Act: -0.0001

Data Index: 270115 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7772. Min Act: -0.0001

Data Index: 533240 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7171. Min Act: -0.0001

Data Index: 1305030 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7502. Min Act: -0.0001

Data Index: 1147589 (C4 (Web Text))

Max Activating Token Index: 937