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

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

Neuron 3388 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: 0.8539. Min Range: -0.8539

Max Act: 0.8539. Min Act: -0.0000

Data Index: 264568 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.8314. Min Act: -0.0000

Data Index: 906519 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.8136. Min Act: -0.0000

Data Index: 809877 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1082973 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7657. Min Act: -0.0000

Data Index: 252230 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7741. Min Act: -0.0000

Data Index: 1118597 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7477. Min Act: -0.0000

Data Index: 853517 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.8098. Min Act: -0.0000

Data Index: 1310320 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1128725 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7752. Min Act: -0.0000

Data Index: 466120 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7486. Min Act: -0.0000

Data Index: 783932 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7207. Min Act: -0.0000

Data Index: 788422 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7147. Min Act: -0.0000

Data Index: 250114 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7239. Min Act: -0.0000

Data Index: 533258 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7426. Min Act: -0.0000

Data Index: 198187 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1182157 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6999. Min Act: -0.0000

Data Index: 1237677 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6896. Min Act: -0.0000

Data Index: 782370 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6948. Min Act: -0.0000

Data Index: 932301 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6733. Min Act: -0.0000

Data Index: 927420 (C4 (Web Text))

Max Activating Token Index: 922