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

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

Neuron 3020 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: 0.1233. Min Range: -0.1233

Max Act: 0.1233. Min Act: -0.0001

Data Index: 347419 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1081. Min Act: -0.0001

Data Index: 735225 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.1086. Min Act: -0.0001

Data Index: 922328 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0948. Min Act: -0.0001

Data Index: 635127 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0940. Min Act: -0.0001

Data Index: 879965 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0816. Min Act: -0.0001

Data Index: 325618 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0894. Min Act: -0.0001

Data Index: 508300 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0798. Min Act: -0.0001

Data Index: 880559 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0839. Min Act: -0.0001

Data Index: 757897 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0802. Min Act: -0.0001

Data Index: 175643 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0795. Min Act: -0.0001

Data Index: 1232906 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1091584 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0787. Min Act: -0.0001

Data Index: 199560 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0753. Min Act: -0.0001

Data Index: 669544 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0773. Min Act: -0.0001

Data Index: 1045261 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0769. Min Act: -0.0001

Data Index: 1255833 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0769. Min Act: -0.0001

Data Index: 787004 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0735. Min Act: -0.0001

Data Index: 603543 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0728. Min Act: -0.0001

Data Index: 1308061 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.1233. Min Range: -0.1233

Max Act: 0.0735. Min Act: -0.0001

Data Index: 215957 (C4 (Web Text))

Max Activating Token Index: 302