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

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

Neuron 2328 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5593. Min Act: -0.0000

Data Index: 813764 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5958. Min Act: -0.0000

Data Index: 682771 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1141807 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5186. Min Act: -0.0000

Data Index: 101086 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1217144 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5757. Min Act: -0.0000

Data Index: 33199 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5564. Min Act: -0.0000

Data Index: 1340319 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5079. Min Act: -0.0000

Data Index: 825875 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1299377 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4979. Min Act: -0.0000

Data Index: 20973 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5043. Min Act: -0.0000

Data Index: 747762 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4587. Min Act: -0.0000

Data Index: 902298 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4870. Min Act: -0.0000

Data Index: 582051 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4549. Min Act: -0.0000

Data Index: 130526 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4906. Min Act: -0.0000

Data Index: 399446 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4419. Min Act: -0.0000

Data Index: 529429 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1103358 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4988. Min Act: -0.0000

Data Index: 199457 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.5035. Min Act: -0.0000

Data Index: 587745 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.5958. Min Range: -0.5958

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1351346 (C4 (Web Text))

Max Activating Token Index: 530