Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1526 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2607. Min Act: -0.0001

Data Index: 40380 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2004. Min Act: -0.0001

Data Index: 1110687 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2318. Min Act: -0.0001

Data Index: 1006970 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2248. Min Act: -0.0001

Data Index: 141264 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2465. Min Act: -0.0001

Data Index: 837974 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2410. Min Act: -0.0001

Data Index: 136703 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2152. Min Act: -0.0001

Data Index: 536253 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2085. Min Act: -0.0001

Data Index: 1345665 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2752. Min Act: -0.0001

Data Index: 539892 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1906. Min Act: -0.0001

Data Index: 643988 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1981. Min Act: -0.0001

Data Index: 1121073 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2047. Min Act: -0.0001

Data Index: 631468 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2087. Min Act: -0.0001

Data Index: 929043 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1831. Min Act: -0.0001

Data Index: 792791 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1715. Min Act: -0.0001

Data Index: 300170 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1938. Min Act: -0.0001

Data Index: 999087 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1782. Min Act: -0.0001

Data Index: 150538 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1905. Min Act: -0.0001

Data Index: 1212670 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1826. Min Act: -0.0001

Data Index: 494523 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.1839. Min Act: -0.0001

Data Index: 299300 (C4 (Web Text))

Max Activating Token Index: 906