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

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

Neuron 1854 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.4613. Min Act: -0.0001

Data Index: 1325460 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 1.4613. Min Range: -1.4613

Max Act: 0.9539. Min Act: -0.0001

Data Index: 729342 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 1.4613. Min Range: -1.4613

Max Act: 0.9675. Min Act: -0.0001

Data Index: 953496 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 1.4613. Min Range: -1.4613

Max Act: 1.0258. Min Act: -0.0001

Data Index: 438870 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 1.4613. Min Range: -1.4613

Max Act: 0.9276. Min Act: -0.0001

Data Index: 52510 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 1.4613. Min Range: -1.4613

Max Act: 0.9428. Min Act: -0.0001

Data Index: 593954 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 1.4613. Min Range: -1.4613

Max Act: 0.8823. Min Act: -0.0001

Data Index: 326946 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 1.4613. Min Range: -1.4613

Max Act: 0.8638. Min Act: -0.0001

Data Index: 651715 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 1.4613. Min Range: -1.4613

Max Act: 0.8508. Min Act: -0.0001

Data Index: 1265629 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 1.4613. Min Range: -1.4613

Max Act: 0.9163. Min Act: -0.0001

Data Index: 457290 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 1.4613. Min Range: -1.4613

Max Act: 0.8907. Min Act: -0.0001

Data Index: 1236264 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 1.4613. Min Range: -1.4613

Max Act: 0.8153. Min Act: -0.0001

Data Index: 1260546 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 1.4613. Min Range: -1.4613

Max Act: 0.8130. Min Act: -0.0001

Data Index: 416634 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 1.4613. Min Range: -1.4613

Max Act: 0.7832. Min Act: -0.0001

Data Index: 810435 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 1.4613. Min Range: -1.4613

Max Act: 0.8607. Min Act: -0.0001

Data Index: 350390 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 1.4613. Min Range: -1.4613

Max Act: 0.8567. Min Act: -0.0001

Data Index: 110905 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 1.4613. Min Range: -1.4613

Max Act: 0.8524. Min Act: -0.0001

Data Index: 826278 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 1.4613. Min Range: -1.4613

Max Act: 0.8492. Min Act: -0.0001

Data Index: 662689 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 1.4613. Min Range: -1.4613

Max Act: 0.8276. Min Act: -0.0001

Data Index: 867103 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 1.4613. Min Range: -1.4613

Max Act: 0.8727. Min Act: -0.0001

Data Index: 685940 (C4 (Web Text))

Max Activating Token Index: 239