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

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

Neuron 3246 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.2254. Min Range: -4.2254

Max Act: 4.2254. Min Act: -0.0000

Data Index: 985877 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 4.2254. Min Range: -4.2254

Max Act: 3.9508. Min Act: -0.0000

Data Index: 787766 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 4.2254. Min Range: -4.2254

Max Act: 3.5082. Min Act: -0.0000

Data Index: 756906 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 4.2254. Min Range: -4.2254

Max Act: 3.3934. Min Act: -0.0000

Data Index: 555693 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 4.2254. Min Range: -4.2254

Max Act: 3.5532. Min Act: -0.0000

Data Index: 855580 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 4.2254. Min Range: -4.2254

Max Act: 3.3924. Min Act: -0.0000

Data Index: 375870 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 4.2254. Min Range: -4.2254

Max Act: 3.1272. Min Act: -0.0000

Data Index: 979390 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 4.2254. Min Range: -4.2254

Max Act: 3.2307. Min Act: -0.0000

Data Index: 680595 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 4.2254. Min Range: -4.2254

Max Act: 2.9895. Min Act: -0.0000

Data Index: 1213223 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 4.2254. Min Range: -4.2254

Max Act: 2.9151. Min Act: -0.0000

Data Index: 641705 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 4.2254. Min Range: -4.2254

Max Act: 3.0523. Min Act: -0.0000

Data Index: 1311976 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 4.2254. Min Range: -4.2254

Max Act: 2.7883. Min Act: -0.0000

Data Index: 1241126 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 4.2254. Min Range: -4.2254

Max Act: 3.1272. Min Act: -0.0000

Data Index: 1337248 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 4.2254. Min Range: -4.2254

Max Act: 2.8271. Min Act: -0.0000

Data Index: 181819 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 4.2254. Min Range: -4.2254

Max Act: 2.8401. Min Act: -0.0000

Data Index: 1117590 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 4.2254. Min Range: -4.2254

Max Act: 2.7997. Min Act: -0.0000

Data Index: 958812 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 4.2254. Min Range: -4.2254

Max Act: 2.7977. Min Act: -0.0000

Data Index: 543265 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 4.2254. Min Range: -4.2254

Max Act: 3.1704. Min Act: -0.0000

Data Index: 796840 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 4.2254. Min Range: -4.2254

Max Act: 2.7370. Min Act: -0.0000

Data Index: 744645 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 4.2254. Min Range: -4.2254

Max Act: 2.9869. Min Act: -0.0000

Data Index: 924220 (C4 (Web Text))

Max Activating Token Index: 164