Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3275 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.4518. Min Act: -0.0001

Data Index: 56316 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 1.4518. Min Range: -1.4518

Max Act: 1.1101. Min Act: -0.0001

Data Index: 802253 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 1.4518. Min Range: -1.4518

Max Act: 0.9387. Min Act: -0.0000

Data Index: 682968 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 1.4518. Min Range: -1.4518

Max Act: 0.8584. Min Act: -0.0000

Data Index: 384971 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 1.4518. Min Range: -1.4518

Max Act: 0.8443. Min Act: -0.0000

Data Index: 46706 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 1.4518. Min Range: -1.4518

Max Act: 0.8003. Min Act: -0.0001

Data Index: 444226 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 1.4518. Min Range: -1.4518

Max Act: 0.7354. Min Act: -0.0001

Data Index: 829010 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 1.4518. Min Range: -1.4518

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1011591 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 1.4518. Min Range: -1.4518

Max Act: 0.6524. Min Act: -0.0000

Data Index: 579133 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 1.4518. Min Range: -1.4518

Max Act: 0.6746. Min Act: -0.0001

Data Index: 1265499 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 1.4518. Min Range: -1.4518

Max Act: 0.7058. Min Act: -0.0001

Data Index: 673317 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 1.4518. Min Range: -1.4518

Max Act: 0.6733. Min Act: -0.0001

Data Index: 161892 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 1.4518. Min Range: -1.4518

Max Act: 0.6635. Min Act: -0.0000

Data Index: 69216 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 1.4518. Min Range: -1.4518

Max Act: 0.6575. Min Act: -0.0000

Data Index: 218689 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 1.4518. Min Range: -1.4518

Max Act: 0.6269. Min Act: -0.0001

Data Index: 696356 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 1.4518. Min Range: -1.4518

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1040469 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 1.4518. Min Range: -1.4518

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1289603 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 1.4518. Min Range: -1.4518

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1008866 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 1.4518. Min Range: -1.4518

Max Act: 0.6093. Min Act: -0.0001

Data Index: 834447 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 1.4518. Min Range: -1.4518

Max Act: 0.6332. Min Act: -0.0001

Data Index: 792430 (C4 (Web Text))

Max Activating Token Index: 927