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

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

Neuron 53 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7178. Min Range: -3.7178

Max Act: 3.7178. Min Act: -0.0000

Data Index: 822956 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 3.7178. Min Range: -3.7178

Max Act: 3.3067. Min Act: -0.0000

Data Index: 634999 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 3.7178. Min Range: -3.7178

Max Act: 3.0095. Min Act: -0.0000

Data Index: 552744 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 3.7178. Min Range: -3.7178

Max Act: 2.7204. Min Act: -0.0000

Data Index: 542187 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 3.7178. Min Range: -3.7178

Max Act: 2.8233. Min Act: -0.0000

Data Index: 753962 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 3.7178. Min Range: -3.7178

Max Act: 3.2215. Min Act: -0.0000

Data Index: 938138 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 3.7178. Min Range: -3.7178

Max Act: 2.5327. Min Act: -0.0000

Data Index: 1101301 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 3.7178. Min Range: -3.7178

Max Act: 2.6075. Min Act: -0.0000

Data Index: 246756 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 3.7178. Min Range: -3.7178

Max Act: 2.4278. Min Act: -0.0000

Data Index: 660909 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 3.7178. Min Range: -3.7178

Max Act: 2.0960. Min Act: -0.0000

Data Index: 1029668 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 3.7178. Min Range: -3.7178

Max Act: 2.1638. Min Act: -0.0000

Data Index: 1155398 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 3.7178. Min Range: -3.7178

Max Act: 2.0335. Min Act: -0.0000

Data Index: 715606 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 3.7178. Min Range: -3.7178

Max Act: 2.0510. Min Act: -0.0000

Data Index: 49223 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 3.7178. Min Range: -3.7178

Max Act: 2.0070. Min Act: -0.0000

Data Index: 421320 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 3.7178. Min Range: -3.7178

Max Act: 1.9866. Min Act: 0.0000

Data Index: 506889 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 3.7178. Min Range: -3.7178

Max Act: 1.9388. Min Act: -0.0000

Data Index: 365601 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 3.7178. Min Range: -3.7178

Max Act: 1.9275. Min Act: -0.0000

Data Index: 190048 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 3.7178. Min Range: -3.7178

Max Act: 1.9514. Min Act: -0.0000

Data Index: 1079677 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 3.7178. Min Range: -3.7178

Max Act: 1.9303. Min Act: -0.0000

Data Index: 928748 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 3.7178. Min Range: -3.7178

Max Act: 1.6933. Min Act: -0.0000

Data Index: 252711 (C4 (Web Text))

Max Activating Token Index: 110