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

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

Neuron 5299 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1412. Min Range: -2.1412

Max Act: 2.1412. Min Act: -0.0000

Data Index: 949714 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 2.1412. Min Range: -2.1412

Max Act: 1.7138. Min Act: -0.0000

Data Index: 1236106 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 2.1412. Min Range: -2.1412

Max Act: 1.5646. Min Act: -0.0000

Data Index: 158682 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 2.1412. Min Range: -2.1412

Max Act: 1.4399. Min Act: -0.0000

Data Index: 997703 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 2.1412. Min Range: -2.1412

Max Act: 1.4094. Min Act: -0.0000

Data Index: 821780 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 2.1412. Min Range: -2.1412

Max Act: 1.4473. Min Act: -0.0001

Data Index: 440256 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 2.1412. Min Range: -2.1412

Max Act: 1.2667. Min Act: -0.0000

Data Index: 117085 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 2.1412. Min Range: -2.1412

Max Act: 1.3371. Min Act: -0.0000

Data Index: 626806 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 2.1412. Min Range: -2.1412

Max Act: 1.4507. Min Act: -0.0000

Data Index: 149663 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 2.1412. Min Range: -2.1412

Max Act: 1.3793. Min Act: -0.0001

Data Index: 223978 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 2.1412. Min Range: -2.1412

Max Act: 1.3319. Min Act: -0.0000

Data Index: 229171 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 2.1412. Min Range: -2.1412

Max Act: 1.2244. Min Act: -0.0001

Data Index: 117081 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 2.1412. Min Range: -2.1412

Max Act: 1.1730. Min Act: -0.0000

Data Index: 1301095 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 2.1412. Min Range: -2.1412

Max Act: 1.3063. Min Act: -0.0000

Data Index: 662123 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 2.1412. Min Range: -2.1412

Max Act: 1.1879. Min Act: -0.0000

Data Index: 104274 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 2.1412. Min Range: -2.1412

Max Act: 1.2588. Min Act: -0.0000

Data Index: 170289 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 2.1412. Min Range: -2.1412

Max Act: 1.1444. Min Act: -0.0000

Data Index: 673779 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 2.1412. Min Range: -2.1412

Max Act: 1.0707. Min Act: -0.0000

Data Index: 477510 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 2.1412. Min Range: -2.1412

Max Act: 1.1148. Min Act: -0.0000

Data Index: 1327255 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 2.1412. Min Range: -2.1412

Max Act: 1.0487. Min Act: -0.0001

Data Index: 260288 (C4 (Web Text))

Max Activating Token Index: 624