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

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

Neuron 3103 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: 4.8077. Min Range: -4.8077

Max Act: 4.8077. Min Act: -0.0000

Data Index: 1198202 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 4.8077. Min Range: -4.8077

Max Act: 4.4767. Min Act: -0.0000

Data Index: 1070106 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 4.8077. Min Range: -4.8077

Max Act: 4.3329. Min Act: -0.0000

Data Index: 801600 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 4.8077. Min Range: -4.8077

Max Act: 4.4506. Min Act: -0.0000

Data Index: 1356709 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 4.8077. Min Range: -4.8077

Max Act: 4.5626. Min Act: -0.0000

Data Index: 804470 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 4.8077. Min Range: -4.8077

Max Act: 4.4018. Min Act: -0.0000

Data Index: 648196 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 4.8077. Min Range: -4.8077

Max Act: 4.2129. Min Act: -0.0000

Data Index: 89658 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 4.8077. Min Range: -4.8077

Max Act: 3.8041. Min Act: -0.0000

Data Index: 381874 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 4.8077. Min Range: -4.8077

Max Act: 4.1312. Min Act: -0.0000

Data Index: 632512 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 4.8077. Min Range: -4.8077

Max Act: 3.6382. Min Act: -0.0000

Data Index: 67790 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 4.8077. Min Range: -4.8077

Max Act: 3.6172. Min Act: -0.0000

Data Index: 29686 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 4.8077. Min Range: -4.8077

Max Act: 3.1072. Min Act: -0.0000

Data Index: 195433 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 4.8077. Min Range: -4.8077

Max Act: 2.8318. Min Act: -0.0000

Data Index: 140639 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 4.8077. Min Range: -4.8077

Max Act: 2.9422. Min Act: -0.0000

Data Index: 1252393 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 4.8077. Min Range: -4.8077

Max Act: 2.7846. Min Act: -0.0000

Data Index: 586964 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 4.8077. Min Range: -4.8077

Max Act: 2.9923. Min Act: -0.0000

Data Index: 753399 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 4.8077. Min Range: -4.8077

Max Act: 2.9646. Min Act: -0.0000

Data Index: 988470 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 4.8077. Min Range: -4.8077

Max Act: 2.9389. Min Act: -0.0000

Data Index: 392701 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 4.8077. Min Range: -4.8077

Max Act: 2.7926. Min Act: -0.0000

Data Index: 893541 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 4.8077. Min Range: -4.8077

Max Act: 2.5972. Min Act: -0.0000

Data Index: 902511 (C4 (Web Text))

Max Activating Token Index: 729