Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5735 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.5980. Min Act: -0.0000

Data Index: 735382 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1348407 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4966. Min Act: -0.0000

Data Index: 547654 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1003421 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4847. Min Act: -0.0000

Data Index: 736709 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4478. Min Act: -0.0000

Data Index: 836873 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4462. Min Act: -0.0000

Data Index: 772999 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4587. Min Act: -0.0000

Data Index: 1042172 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4709. Min Act: -0.0000

Data Index: 482214 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4563. Min Act: 0.0000

Data Index: 1083357 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4389. Min Act: -0.0000

Data Index: 200159 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1206238 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4303. Min Act: -0.0000

Data Index: 560424 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4414. Min Act: -0.0000

Data Index: 323126 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4417. Min Act: -0.0000

Data Index: 380020 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4564. Min Act: -0.0000

Data Index: 699100 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4354. Min Act: -0.0000

Data Index: 1253187 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4372. Min Act: -0.0000

Data Index: 108117 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4337. Min Act: -0.0000

Data Index: 1176549 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4145. Min Act: -0.0000

Data Index: 136316 (C4 (Web Text))

Max Activating Token Index: 504