Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1993 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.4516. Min Act: -0.0000

Data Index: 919031 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.3008. Min Act: -0.0000

Data Index: 503294 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.1755. Min Act: -0.0000

Data Index: 1028623 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.2563. Min Act: -0.0000

Data Index: 1068099 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.1997. Min Act: -0.0000

Data Index: 761658 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.3262. Min Act: -0.0000

Data Index: 1227185 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.3335. Min Act: -0.0000

Data Index: 552781 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.0774. Min Act: -0.0000

Data Index: 167193 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 2.4516. Min Range: -2.4516

Max Act: 1.8537. Min Act: -0.0000

Data Index: 484116 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.0600. Min Act: -0.0000

Data Index: 907036 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.1647. Min Act: -0.0000

Data Index: 723311 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.0419. Min Act: -0.0000

Data Index: 231838 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.0042. Min Act: -0.0000

Data Index: 21814 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 2.4516. Min Range: -2.4516

Max Act: 1.9891. Min Act: -0.0000

Data Index: 759189 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 2.4516. Min Range: -2.4516

Max Act: 1.9822. Min Act: -0.0000

Data Index: 232503 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.0618. Min Act: -0.0000

Data Index: 1273852 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 2.4516. Min Range: -2.4516

Max Act: 1.9495. Min Act: -0.0000

Data Index: 1263499 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 2.4516. Min Range: -2.4516

Max Act: 1.8149. Min Act: -0.0000

Data Index: 511807 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.0079. Min Act: -0.0000

Data Index: 973489 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 2.4516. Min Range: -2.4516

Max Act: 1.9974. Min Act: -0.0000

Data Index: 1290565 (C4 (Web Text))

Max Activating Token Index: 816