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

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

Neuron 5547 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2974. Min Range: -1.2974

Max Act: 1.2974. Min Act: -0.0000

Data Index: 1335883 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 1.2974. Min Range: -1.2974

Max Act: 1.1861. Min Act: -0.0000

Data Index: 330206 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 1.2974. Min Range: -1.2974

Max Act: 0.9252. Min Act: 0.0000

Data Index: 414355 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 1.2974. Min Range: -1.2974

Max Act: 0.9564. Min Act: -0.0000

Data Index: 242833 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 1.2974. Min Range: -1.2974

Max Act: 0.7521. Min Act: -0.0000

Data Index: 1151056 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 1.2974. Min Range: -1.2974

Max Act: 0.7418. Min Act: -0.0000

Data Index: 1013217 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 1.2974. Min Range: -1.2974

Max Act: 0.7822. Min Act: -0.0000

Data Index: 851663 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 1.2974. Min Range: -1.2974

Max Act: 0.7228. Min Act: -0.0000

Data Index: 391928 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 1.2974. Min Range: -1.2974

Max Act: 0.7988. Min Act: -0.0000

Data Index: 176240 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 1.2974. Min Range: -1.2974

Max Act: 0.7154. Min Act: -0.0000

Data Index: 266104 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 1.2974. Min Range: -1.2974

Max Act: 0.6951. Min Act: -0.0000

Data Index: 695180 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 1.2974. Min Range: -1.2974

Max Act: 0.7139. Min Act: -0.0000

Data Index: 366098 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 1.2974. Min Range: -1.2974

Max Act: 0.6924. Min Act: -0.0000

Data Index: 327757 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 1.2974. Min Range: -1.2974

Max Act: 0.6677. Min Act: -0.0000

Data Index: 224969 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 1.2974. Min Range: -1.2974

Max Act: 0.6554. Min Act: -0.0000

Data Index: 181164 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 1.2974. Min Range: -1.2974

Max Act: 0.6503. Min Act: -0.0000

Data Index: 601146 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 1.2974. Min Range: -1.2974

Max Act: 0.6689. Min Act: 0.0001

Data Index: 187255 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 1.2974. Min Range: -1.2974

Max Act: 0.6841. Min Act: -0.0000

Data Index: 265816 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 1.2974. Min Range: -1.2974

Max Act: 0.6398. Min Act: 0.0000

Data Index: 1233456 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 1.2974. Min Range: -1.2974

Max Act: 0.6737. Min Act: 0.0000

Data Index: 459872 (C4 (Web Text))

Max Activating Token Index: 480