Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 324 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.6198. Min Act: -0.0003

Data Index: 949563 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4882. Min Act: -0.0003

Data Index: 876060 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4579. Min Act: -0.0003

Data Index: 298729 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4699. Min Act: -0.0003

Data Index: 1093128 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4306. Min Act: -0.0003

Data Index: 202536 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4403. Min Act: -0.0002

Data Index: 348106 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4450. Min Act: -0.0002

Data Index: 243182 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4227. Min Act: -0.0003

Data Index: 540680 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4161. Min Act: -0.0003

Data Index: 863182 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4277. Min Act: -0.0002

Data Index: 395446 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4081. Min Act: -0.0002

Data Index: 611070 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4185. Min Act: -0.0003

Data Index: 813225 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4046. Min Act: -0.0003

Data Index: 428387 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4053. Min Act: -0.0003

Data Index: 1009870 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.4029. Min Act: -0.0003

Data Index: 1199800 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.3984. Min Act: -0.0002

Data Index: 855299 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.3835. Min Act: -0.0003

Data Index: 994278 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.3984. Min Act: -0.0003

Data Index: 489146 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.3921. Min Act: -0.0003

Data Index: 689152 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.6198. Min Range: -0.6198

Max Act: 0.3901. Min Act: -0.0003

Data Index: 667615 (C4 (Web Text))

Max Activating Token Index: 700