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

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

Neuron 2918 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: 0.8328. Min Range: -0.8328

Max Act: 0.8328. Min Act: -0.0000

Data Index: 1185290 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.8328. Min Range: -0.8328

Max Act: 0.7977. Min Act: -0.0000

Data Index: 805829 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 0.8328. Min Range: -0.8328

Max Act: 0.6532. Min Act: -0.0000

Data Index: 157919 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.8328. Min Range: -0.8328

Max Act: 0.6696. Min Act: -0.0000

Data Index: 307868 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.8328. Min Range: -0.8328

Max Act: 0.6995. Min Act: -0.0000

Data Index: 624820 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.8328. Min Range: -0.8328

Max Act: 0.6665. Min Act: -0.0000

Data Index: 720541 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 0.8328. Min Range: -0.8328

Max Act: 0.6630. Min Act: -0.0000

Data Index: 1256442 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.8328. Min Range: -0.8328

Max Act: 0.6321. Min Act: -0.0000

Data Index: 819843 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.8328. Min Range: -0.8328

Max Act: 0.6299. Min Act: -0.0000

Data Index: 425572 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.8328. Min Range: -0.8328

Max Act: 0.6671. Min Act: -0.0000

Data Index: 272712 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.8328. Min Range: -0.8328

Max Act: 0.6391. Min Act: -0.0000

Data Index: 820810 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.8328. Min Range: -0.8328

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1224113 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.8328. Min Range: -0.8328

Max Act: 0.6049. Min Act: -0.0000

Data Index: 633355 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.8328. Min Range: -0.8328

Max Act: 0.6380. Min Act: -0.0000

Data Index: 149873 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.8328. Min Range: -0.8328

Max Act: 0.6375. Min Act: -0.0000

Data Index: 120 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.8328. Min Range: -0.8328

Max Act: 0.6170. Min Act: -0.0000

Data Index: 119411 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.8328. Min Range: -0.8328

Max Act: 0.5936. Min Act: -0.0000

Data Index: 600458 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.8328. Min Range: -0.8328

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1313076 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.8328. Min Range: -0.8328

Max Act: 0.6094. Min Act: -0.0000

Data Index: 728081 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.8328. Min Range: -0.8328

Max Act: 0.5907. Min Act: -0.0000

Data Index: 375873 (C4 (Web Text))

Max Activating Token Index: 370