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

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

Neuron 718 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: 0.7383. Min Range: -0.7383

Max Act: 0.7383. Min Act: -0.0000

Data Index: 1072087 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.7383. Min Range: -0.7383

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1054864 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.7383. Min Range: -0.7383

Max Act: 0.7196. Min Act: -0.0000

Data Index: 583685 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.7383. Min Range: -0.7383

Max Act: 0.7345. Min Act: -0.0000

Data Index: 1361775 (Python Code)

Max Activating Token Index: 955

Text #4

Max Range: 0.7383. Min Range: -0.7383

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1461221 (Python Code)

Max Activating Token Index: 194

Text #5

Max Range: 0.7383. Min Range: -0.7383

Max Act: 0.6883. Min Act: -0.0000

Data Index: 1400255 (Python Code)

Max Activating Token Index: 614

Text #6

Max Range: 0.7383. Min Range: -0.7383

Max Act: 0.7068. Min Act: -0.0000

Data Index: 1623361 (Python Code)

Max Activating Token Index: 128

Text #7

Max Range: 0.7383. Min Range: -0.7383

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1203296 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.7383. Min Range: -0.7383

Max Act: 0.6477. Min Act: -0.0000

Data Index: 791666 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.7383. Min Range: -0.7383

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1334146 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.7383. Min Range: -0.7383

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1306030 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 0.7383. Min Range: -0.7383

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1591844 (Python Code)

Max Activating Token Index: 706

Text #12

Max Range: 0.7383. Min Range: -0.7383

Max Act: 0.6495. Min Act: -0.0000

Data Index: 1641682 (Python Code)

Max Activating Token Index: 931

Text #13

Max Range: 0.7383. Min Range: -0.7383

Max Act: 0.6038. Min Act: -0.0000

Data Index: 642404 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.7383. Min Range: -0.7383

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1480586 (Python Code)

Max Activating Token Index: 942

Text #15

Max Range: 0.7383. Min Range: -0.7383

Max Act: 0.6258. Min Act: -0.0000

Data Index: 5379 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.7383. Min Range: -0.7383

Max Act: 0.6008. Min Act: -0.0000

Data Index: 223563 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.7383. Min Range: -0.7383

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1655044 (Python Code)

Max Activating Token Index: 147

Text #18

Max Range: 0.7383. Min Range: -0.7383

Max Act: 0.5572. Min Act: -0.0000

Data Index: 1498878 (Python Code)

Max Activating Token Index: 64

Text #19

Max Range: 0.7383. Min Range: -0.7383

Max Act: 0.5693. Min Act: -0.0000

Data Index: 402004 (C4 (Web Text))

Max Activating Token Index: 785