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

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

Neuron 3472 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.6277. Min Act: -0.0000

Data Index: 1308622 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.4804. Min Act: -0.0000

Data Index: 570219 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.4406. Min Act: -0.0000

Data Index: 160220 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.3649. Min Act: -0.0000

Data Index: 997791 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.2515. Min Act: -0.0000

Data Index: 1172391 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.3591. Min Act: -0.0000

Data Index: 1084031 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.2829. Min Act: -0.0000

Data Index: 730744 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.2364. Min Act: -0.0000

Data Index: 334723 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.2565. Min Act: -0.0000

Data Index: 844190 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.3450. Min Act: -0.0000

Data Index: 818446 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.2818. Min Act: -0.0000

Data Index: 1045624 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.2808. Min Act: -0.0000

Data Index: 234063 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.1629. Min Act: -0.0000

Data Index: 1176449 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.2402. Min Act: -0.0000

Data Index: 1013842 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.2079. Min Act: -0.0000

Data Index: 1062168 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.1724. Min Act: -0.0000

Data Index: 200666 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.1758. Min Act: -0.0000

Data Index: 93280 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.0626. Min Act: -0.0000

Data Index: 203122 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.0617. Min Act: -0.0000

Data Index: 105356 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 1.6277. Min Range: -1.6277

Max Act: 1.0536. Min Act: -0.0000

Data Index: 684147 (C4 (Web Text))

Max Activating Token Index: 171