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

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

Neuron 676 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3778. Min Range: -1.3778

Max Act: 1.3129. Min Act: -0.0001

Data Index: 717027 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 1.3778. Min Range: -1.3778

Max Act: 1.3778. Min Act: -0.0001

Data Index: 1064095 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 1.3778. Min Range: -1.3778

Max Act: 1.1396. Min Act: -0.0001

Data Index: 1330336 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 1.3778. Min Range: -1.3778

Max Act: 1.1166. Min Act: -0.0001

Data Index: 1172499 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 1.3778. Min Range: -1.3778

Max Act: 1.1122. Min Act: -0.0001

Data Index: 268260 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 1.3778. Min Range: -1.3778

Max Act: 1.1030. Min Act: -0.0001

Data Index: 1162228 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 1.3778. Min Range: -1.3778

Max Act: 1.0084. Min Act: -0.0001

Data Index: 217571 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 1.3778. Min Range: -1.3778

Max Act: 1.0436. Min Act: -0.0001

Data Index: 431608 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 1.3778. Min Range: -1.3778

Max Act: 0.9547. Min Act: -0.0001

Data Index: 896869 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 1.3778. Min Range: -1.3778

Max Act: 1.0338. Min Act: -0.0001

Data Index: 1355432 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 1.3778. Min Range: -1.3778

Max Act: 1.0272. Min Act: -0.0001

Data Index: 1181591 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 1.3778. Min Range: -1.3778

Max Act: 0.9818. Min Act: -0.0001

Data Index: 164399 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 1.3778. Min Range: -1.3778

Max Act: 1.0462. Min Act: -0.0001

Data Index: 1194680 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 1.3778. Min Range: -1.3778

Max Act: 1.0116. Min Act: -0.0001

Data Index: 1050170 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 1.3778. Min Range: -1.3778

Max Act: 0.9456. Min Act: -0.0001

Data Index: 239511 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 1.3778. Min Range: -1.3778

Max Act: 0.8470. Min Act: -0.0001

Data Index: 32507 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 1.3778. Min Range: -1.3778

Max Act: 0.8702. Min Act: -0.0001

Data Index: 1245619 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 1.3778. Min Range: -1.3778

Max Act: 0.9933. Min Act: -0.0001

Data Index: 972356 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 1.3778. Min Range: -1.3778

Max Act: 0.9614. Min Act: -0.0001

Data Index: 246659 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 1.3778. Min Range: -1.3778

Max Act: 0.9877. Min Act: -0.0001

Data Index: 151357 (C4 (Web Text))

Max Activating Token Index: 42