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

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

Neuron 823 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6096. Min Range: -2.6096

Max Act: 2.6096. Min Act: -0.0000

Data Index: 504226 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 2.6096. Min Range: -2.6096

Max Act: 2.6071. Min Act: -0.0000

Data Index: 106470 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 2.6096. Min Range: -2.6096

Max Act: 2.4611. Min Act: -0.0000

Data Index: 746711 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 2.6096. Min Range: -2.6096

Max Act: 2.4816. Min Act: -0.0000

Data Index: 60300 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 2.6096. Min Range: -2.6096

Max Act: 2.4106. Min Act: -0.0000

Data Index: 499503 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 2.6096. Min Range: -2.6096

Max Act: 2.3826. Min Act: -0.0000

Data Index: 637154 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 2.6096. Min Range: -2.6096

Max Act: 2.3542. Min Act: -0.0000

Data Index: 529051 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 2.6096. Min Range: -2.6096

Max Act: 2.4638. Min Act: -0.0000

Data Index: 603217 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 2.6096. Min Range: -2.6096

Max Act: 2.3152. Min Act: -0.0000

Data Index: 803622 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 2.6096. Min Range: -2.6096

Max Act: 2.3102. Min Act: -0.0000

Data Index: 1104804 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 2.6096. Min Range: -2.6096

Max Act: 2.2671. Min Act: -0.0000

Data Index: 873276 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 2.6096. Min Range: -2.6096

Max Act: 2.2613. Min Act: -0.0000

Data Index: 1047706 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 2.6096. Min Range: -2.6096

Max Act: 2.1199. Min Act: -0.0000

Data Index: 1223111 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 2.6096. Min Range: -2.6096

Max Act: 2.1951. Min Act: -0.0000

Data Index: 732374 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 2.6096. Min Range: -2.6096

Max Act: 2.1771. Min Act: -0.0000

Data Index: 1324096 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 2.6096. Min Range: -2.6096

Max Act: 1.9669. Min Act: -0.0000

Data Index: 78186 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 2.6096. Min Range: -2.6096

Max Act: 2.0412. Min Act: -0.0000

Data Index: 642103 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 2.6096. Min Range: -2.6096

Max Act: 2.1448. Min Act: -0.0000

Data Index: 1168365 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 2.6096. Min Range: -2.6096

Max Act: 2.0257. Min Act: -0.0000

Data Index: 1118279 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 2.6096. Min Range: -2.6096

Max Act: 2.0157. Min Act: -0.0000

Data Index: 950377 (C4 (Web Text))

Max Activating Token Index: 749