Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 11 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.9200. Min Act: -0.0001

Data Index: 464802 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.8989. Min Act: -0.0001

Data Index: 406536 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7911. Min Act: -0.0001

Data Index: 202203 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7305. Min Act: -0.0001

Data Index: 85157 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.8696. Min Act: -0.0001

Data Index: 510025 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7380. Min Act: -0.0001

Data Index: 717307 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7604. Min Act: -0.0001

Data Index: 947039 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7300. Min Act: -0.0001

Data Index: 523244 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7129. Min Act: -0.0001

Data Index: 135536 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6783. Min Act: -0.0001

Data Index: 1052426 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7132. Min Act: -0.0001

Data Index: 377949 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7145. Min Act: -0.0001

Data Index: 1330006 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7443. Min Act: -0.0001

Data Index: 64 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6857. Min Act: -0.0001

Data Index: 1284166 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7079. Min Act: -0.0001

Data Index: 1271210 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6813. Min Act: -0.0001

Data Index: 553250 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6592. Min Act: -0.0001

Data Index: 171864 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6971. Min Act: -0.0001

Data Index: 163649 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6988. Min Act: -0.0001

Data Index: 401483 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6686. Min Act: -0.0001

Data Index: 1178007 (C4 (Web Text))

Max Activating Token Index: 812