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

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

Neuron 2004 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: 1.1179. Min Range: -1.1179

Max Act: 1.1179. Min Act: -0.0000

Data Index: 145207 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 1.1179. Min Range: -1.1179

Max Act: 1.0085. Min Act: -0.0000

Data Index: 469374 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9466. Min Act: -0.0000

Data Index: 598915 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8205. Min Act: -0.0000

Data Index: 1182664 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9070. Min Act: -0.0000

Data Index: 875710 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8276. Min Act: -0.0000

Data Index: 751169 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8651. Min Act: -0.0000

Data Index: 678724 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8611. Min Act: -0.0000

Data Index: 626503 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8761. Min Act: -0.0000

Data Index: 144795 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8099. Min Act: -0.0000

Data Index: 289739 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7892. Min Act: -0.0000

Data Index: 956131 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8105. Min Act: -0.0000

Data Index: 821457 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7409. Min Act: -0.0000

Data Index: 240146 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1353423 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7723. Min Act: -0.0000

Data Index: 216428 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7666. Min Act: -0.0000

Data Index: 1171423 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7001. Min Act: -0.0000

Data Index: 221128 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7493. Min Act: -0.0000

Data Index: 552247 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7785. Min Act: -0.0000

Data Index: 1157828 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7100. Min Act: -0.0000

Data Index: 17659 (C4 (Web Text))

Max Activating Token Index: 444