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

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

Neuron 4810 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0220. Min Range: -1.0220

Max Act: 1.0220. Min Act: -0.0001

Data Index: 656229 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.9571. Min Act: -0.0001

Data Index: 422527 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 1.0220. Min Range: -1.0220

Max Act: 1.0204. Min Act: -0.0001

Data Index: 742701 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.8633. Min Act: -0.0001

Data Index: 1005038 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.8956. Min Act: -0.0001

Data Index: 636186 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.8966. Min Act: -0.0001

Data Index: 613852 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.8775. Min Act: -0.0001

Data Index: 1181354 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.8466. Min Act: -0.0001

Data Index: 1079201 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.7759. Min Act: -0.0001

Data Index: 1114260 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.7785. Min Act: -0.0001

Data Index: 691185 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.7218. Min Act: -0.0001

Data Index: 600389 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.7425. Min Act: -0.0001

Data Index: 1239371 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.7650. Min Act: -0.0001

Data Index: 1160684 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.7388. Min Act: -0.0001

Data Index: 600751 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.7450. Min Act: -0.0001

Data Index: 818028 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.7204. Min Act: -0.0001

Data Index: 312531 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.7043. Min Act: -0.0001

Data Index: 146430 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.6981. Min Act: -0.0001

Data Index: 743539 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.6915. Min Act: -0.0001

Data Index: 137980 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 1.0220. Min Range: -1.0220

Max Act: 0.6881. Min Act: -0.0001

Data Index: 1326575 (C4 (Web Text))

Max Activating Token Index: 744