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

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

Neuron 4476 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1500. Min Range: -1.1500

Max Act: 1.1500. Min Act: -0.0000

Data Index: 268725 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 1.1500. Min Range: -1.1500

Max Act: 1.0273. Min Act: 0.0000

Data Index: 853146 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.9638. Min Act: -0.0000

Data Index: 1008303 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.9532. Min Act: -0.0000

Data Index: 424952 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.9197. Min Act: 0.0000

Data Index: 1212860 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.9009. Min Act: -0.0000

Data Index: 525022 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.8389. Min Act: -0.0000

Data Index: 1205016 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.8933. Min Act: -0.0000

Data Index: 209975 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.8192. Min Act: -0.0000

Data Index: 265281 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.8326. Min Act: -0.0000

Data Index: 493276 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.8461. Min Act: 0.0000

Data Index: 702416 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.8456. Min Act: -0.0000

Data Index: 1269650 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.8122. Min Act: 0.0000

Data Index: 1301820 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.7930. Min Act: 0.0000

Data Index: 230293 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.8300. Min Act: -0.0000

Data Index: 758913 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.7766. Min Act: -0.0000

Data Index: 142119 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.8014. Min Act: 0.0000

Data Index: 1074701 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.8137. Min Act: -0.0000

Data Index: 1295714 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.7529. Min Act: -0.0000

Data Index: 487518 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 1.1500. Min Range: -1.1500

Max Act: 0.7859. Min Act: -0.0000

Data Index: 386779 (C4 (Web Text))

Max Activating Token Index: 330