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

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

Neuron 2062 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.6121. Min Act: -0.0000

Data Index: 133111 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.5905. Min Act: -0.0000

Data Index: 92340 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1010866 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.5886. Min Act: -0.0000

Data Index: 91174 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.5724. Min Act: -0.0000

Data Index: 759816 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1068669 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1251518 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.5329. Min Act: -0.0000

Data Index: 732864 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.5356. Min Act: -0.0000

Data Index: 529601 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4981. Min Act: -0.0000

Data Index: 173498 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.5190. Min Act: -0.0000

Data Index: 354109 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4848. Min Act: -0.0000

Data Index: 210082 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4993. Min Act: -0.0000

Data Index: 326708 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4851. Min Act: -0.0000

Data Index: 1276417 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4444. Min Act: -0.0000

Data Index: 222996 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4350. Min Act: -0.0000

Data Index: 824603 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4152. Min Act: -0.0000

Data Index: 196888 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4394. Min Act: -0.0000

Data Index: 579766 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1103446 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.6121. Min Range: -0.6121

Max Act: 0.4278. Min Act: -0.0000

Data Index: 1316184 (C4 (Web Text))

Max Activating Token Index: 887