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

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

Neuron 89 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0083. Min Range: -4.0083

Max Act: 4.0083. Min Act: -0.0000

Data Index: 593230 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.8860. Min Act: -0.0000

Data Index: 695530 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.9239. Min Act: -0.0000

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.1015. Min Act: -0.0000

Data Index: 286659 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.0341. Min Act: -0.0000

Data Index: 893110 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 4.0083. Min Range: -4.0083

Max Act: 2.7923. Min Act: -0.0000

Data Index: 578080 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 4.0083. Min Range: -4.0083

Max Act: 2.9263. Min Act: -0.0000

Data Index: 926822 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 4.0083. Min Range: -4.0083

Max Act: 2.8995. Min Act: -0.0000

Data Index: 278004 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 4.0083. Min Range: -4.0083

Max Act: 2.9051. Min Act: -0.0000

Data Index: 1359589 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 4.0083. Min Range: -4.0083

Max Act: 2.7460. Min Act: -0.0000

Data Index: 790736 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 4.0083. Min Range: -4.0083

Max Act: 2.8185. Min Act: -0.0000

Data Index: 921607 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 4.0083. Min Range: -4.0083

Max Act: 2.8026. Min Act: -0.0000

Data Index: 960688 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 4.0083. Min Range: -4.0083

Max Act: 2.6511. Min Act: -0.0000

Data Index: 607268 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 4.0083. Min Range: -4.0083

Max Act: 2.7334. Min Act: -0.0000

Data Index: 257907 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 4.0083. Min Range: -4.0083

Max Act: 2.8600. Min Act: -0.0000

Data Index: 1021494 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 4.0083. Min Range: -4.0083

Max Act: 2.6467. Min Act: -0.0000

Data Index: 991246 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 4.0083. Min Range: -4.0083

Max Act: 2.6414. Min Act: -0.0000

Data Index: 831681 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 4.0083. Min Range: -4.0083

Max Act: 2.3315. Min Act: -0.0000

Data Index: 1299744 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 4.0083. Min Range: -4.0083

Max Act: 2.4291. Min Act: -0.0000

Data Index: 572599 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 4.0083. Min Range: -4.0083

Max Act: 2.5636. Min Act: -0.0000

Data Index: 617547 (C4 (Web Text))

Max Activating Token Index: 862