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

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

Neuron 2522 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.4194. Min Act: -0.0001

Data Index: 244244 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.3598. Min Act: -0.0000

Data Index: 167316 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.3536. Min Act: -0.0001

Data Index: 636587 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.3067. Min Act: -0.0000

Data Index: 1306188 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.2610. Min Act: -0.0001

Data Index: 1023331 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.2330. Min Act: -0.0000

Data Index: 548030 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.2232. Min Act: -0.0000

Data Index: 52597 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.1199. Min Act: -0.0000

Data Index: 1089114 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.1434. Min Act: -0.0000

Data Index: 794307 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0741. Min Act: -0.0000

Data Index: 1253806 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0881. Min Act: -0.0001

Data Index: 1041574 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0292. Min Act: -0.0000

Data Index: 986644 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0281. Min Act: -0.0000

Data Index: 590391 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 1.4194. Min Range: -1.4194

Max Act: 0.9820. Min Act: -0.0001

Data Index: 1132168 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0352. Min Act: -0.0000

Data Index: 24883 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0129. Min Act: -0.0000

Data Index: 972893 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0046. Min Act: -0.0000

Data Index: 941549 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0284. Min Act: -0.0000

Data Index: 956204 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 1.4194. Min Range: -1.4194

Max Act: 0.9772. Min Act: -0.0001

Data Index: 525299 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0035. Min Act: -0.0000

Data Index: 265769 (C4 (Web Text))

Max Activating Token Index: 543