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

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

Neuron 2051 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1516. Min Range: -2.1516

Max Act: 2.1516. Min Act: -0.0000

Data Index: 209724 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 2.1516. Min Range: -2.1516

Max Act: 2.0552. Min Act: -0.0000

Data Index: 448483 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.8362. Min Act: -0.0000

Data Index: 852053 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.6186. Min Act: -0.0000

Data Index: 703756 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.7486. Min Act: -0.0000

Data Index: 1053764 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.5502. Min Act: -0.0000

Data Index: 79121 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.4898. Min Act: -0.0000

Data Index: 723534 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.4920. Min Act: -0.0000

Data Index: 1287181 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.4770. Min Act: -0.0000

Data Index: 940689 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.4415. Min Act: -0.0000

Data Index: 985309 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.4231. Min Act: -0.0000

Data Index: 919687 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.4106. Min Act: -0.0000

Data Index: 765028 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.3893. Min Act: 0.0000

Data Index: 41490 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.3064. Min Act: -0.0000

Data Index: 577679 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.5374. Min Act: -0.0000

Data Index: 874821 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.3710. Min Act: -0.0000

Data Index: 427979 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.3516. Min Act: -0.0000

Data Index: 1221615 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.2933. Min Act: -0.0000

Data Index: 1060404 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.3845. Min Act: -0.0000

Data Index: 672670 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 2.1516. Min Range: -2.1516

Max Act: 1.2664. Min Act: -0.0000

Data Index: 285753 (C4 (Web Text))

Max Activating Token Index: 839