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

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

Neuron 2897 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.4171. Min Act: -0.0003

Data Index: 752232 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3611. Min Act: -0.0003

Data Index: 50191 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3791. Min Act: -0.0003

Data Index: 355981 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.4042. Min Act: -0.0003

Data Index: 1233085 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3763. Min Act: -0.0003

Data Index: 182282 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3767. Min Act: -0.0003

Data Index: 883789 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3850. Min Act: -0.0003

Data Index: 189785 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.4064. Min Act: -0.0003

Data Index: 533740 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3820. Min Act: -0.0003

Data Index: 566425 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3700. Min Act: -0.0003

Data Index: 955754 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3564. Min Act: -0.0003

Data Index: 283935 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3790. Min Act: -0.0003

Data Index: 277681 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3867. Min Act: -0.0003

Data Index: 670609 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3749. Min Act: -0.0003

Data Index: 968545 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3876. Min Act: -0.0003

Data Index: 757631 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3623. Min Act: -0.0003

Data Index: 751597 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3842. Min Act: -0.0003

Data Index: 1300167 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3588. Min Act: -0.0003

Data Index: 1035758 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3702. Min Act: -0.0003

Data Index: 854828 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3812. Min Act: -0.0003

Data Index: 528375 (C4 (Web Text))

Max Activating Token Index: 501