Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 881 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.9097. Min Act: -0.0001

Data Index: 1014310 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 1.9097. Min Range: -1.9097

Max Act: 1.0677. Min Act: -0.0001

Data Index: 753653 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 1.9097. Min Range: -1.9097

Max Act: 0.9676. Min Act: -0.0001

Data Index: 718896 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 1.9097. Min Range: -1.9097

Max Act: 0.9169. Min Act: -0.0001

Data Index: 375762 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 1.9097. Min Range: -1.9097

Max Act: 0.9531. Min Act: -0.0001

Data Index: 1355908 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 1.9097. Min Range: -1.9097

Max Act: 0.9350. Min Act: -0.0001

Data Index: 359846 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 1.9097. Min Range: -1.9097

Max Act: 0.9533. Min Act: -0.0001

Data Index: 507696 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 1.9097. Min Range: -1.9097

Max Act: 0.8786. Min Act: -0.0001

Data Index: 416097 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 1.9097. Min Range: -1.9097

Max Act: 0.9056. Min Act: -0.0001

Data Index: 776842 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 1.9097. Min Range: -1.9097

Max Act: 0.9125. Min Act: -0.0001

Data Index: 802873 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 1.9097. Min Range: -1.9097

Max Act: 0.8914. Min Act: -0.0001

Data Index: 1182317 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 1.9097. Min Range: -1.9097

Max Act: 0.8215. Min Act: -0.0001

Data Index: 871626 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 1.9097. Min Range: -1.9097

Max Act: 0.8367. Min Act: -0.0001

Data Index: 392677 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 1.9097. Min Range: -1.9097

Max Act: 0.8376. Min Act: -0.0001

Data Index: 485298 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 1.9097. Min Range: -1.9097

Max Act: 0.8299. Min Act: -0.0001

Data Index: 1037256 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 1.9097. Min Range: -1.9097

Max Act: 0.8848. Min Act: -0.0001

Data Index: 482130 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 1.9097. Min Range: -1.9097

Max Act: 0.8283. Min Act: -0.0001

Data Index: 240515 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 1.9097. Min Range: -1.9097

Max Act: 0.8405. Min Act: -0.0001

Data Index: 833187 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 1.9097. Min Range: -1.9097

Max Act: 0.8358. Min Act: -0.0001

Data Index: 520488 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 1.9097. Min Range: -1.9097

Max Act: 0.8715. Min Act: -0.0001

Data Index: 104881 (C4 (Web Text))

Max Activating Token Index: 615