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

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

Neuron 617 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.4532. Min Act: -0.0001

Data Index: 830787 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.4229. Min Act: -0.0001

Data Index: 1271082 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.4221. Min Act: -0.0001

Data Index: 1010387 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.4094. Min Act: -0.0001

Data Index: 1146069 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3911. Min Act: -0.0001

Data Index: 1093625 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3801. Min Act: -0.0001

Data Index: 854335 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3867. Min Act: -0.0001

Data Index: 574159 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3658. Min Act: -0.0001

Data Index: 618951 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3598. Min Act: -0.0001

Data Index: 1199604 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3510. Min Act: -0.0001

Data Index: 901888 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3420. Min Act: -0.0001

Data Index: 571320 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3685. Min Act: -0.0001

Data Index: 699979 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3416. Min Act: -0.0001

Data Index: 725244 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3324. Min Act: -0.0001

Data Index: 166405 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3308. Min Act: -0.0001

Data Index: 355063 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3456. Min Act: -0.0001

Data Index: 647591 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.2987. Min Act: -0.0001

Data Index: 951768 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3527. Min Act: -0.0001

Data Index: 1276752 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3309. Min Act: -0.0001

Data Index: 1061583 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.4532. Min Range: -0.4532

Max Act: 0.3132. Min Act: -0.0001

Data Index: 537257 (C4 (Web Text))

Max Activating Token Index: 948