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

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

Neuron 1620 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.8861. Min Act: -0.0000

Data Index: 1300134 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.7231. Min Act: -0.0000

Data Index: 652799 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1166988 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.6847. Min Act: -0.0000

Data Index: 950139 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.6757. Min Act: -0.0000

Data Index: 705011 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.6485. Min Act: -0.0000

Data Index: 578189 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.6905. Min Act: -0.0000

Data Index: 601904 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.6602. Min Act: -0.0000

Data Index: 566949 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.6614. Min Act: -0.0000

Data Index: 173717 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.6537. Min Act: -0.0000

Data Index: 288655 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.6354. Min Act: -0.0000

Data Index: 725907 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.6747. Min Act: -0.0000

Data Index: 73596 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.5797. Min Act: -0.0000

Data Index: 707020 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.6394. Min Act: -0.0000

Data Index: 836668 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.6108. Min Act: -0.0000

Data Index: 352251 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1211992 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.5941. Min Act: -0.0000

Data Index: 367247 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.5730. Min Act: -0.0000

Data Index: 663208 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.5882. Min Act: -0.0000

Data Index: 285885 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.5699. Min Act: -0.0000

Data Index: 892261 (C4 (Web Text))

Max Activating Token Index: 18