Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4004 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.2956. Min Range: -3.2956

Max Act: 3.2956. Min Act: -0.0001

Data Index: 725532 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 3.2956. Min Range: -3.2956

Max Act: 2.9012. Min Act: -0.0001

Data Index: 462576 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 3.2956. Min Range: -3.2956

Max Act: 2.4140. Min Act: -0.0001

Data Index: 543331 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 3.2956. Min Range: -3.2956

Max Act: 2.0843. Min Act: -0.0001

Data Index: 211221 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 3.2956. Min Range: -3.2956

Max Act: 1.9633. Min Act: -0.0001

Data Index: 1245497 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 3.2956. Min Range: -3.2956

Max Act: 2.0178. Min Act: -0.0001

Data Index: 150281 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 3.2956. Min Range: -3.2956

Max Act: 2.0211. Min Act: -0.0001

Data Index: 619872 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 3.2956. Min Range: -3.2956

Max Act: 1.9480. Min Act: -0.0001

Data Index: 1201237 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 3.2956. Min Range: -3.2956

Max Act: 1.9442. Min Act: -0.0001

Data Index: 145270 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 3.2956. Min Range: -3.2956

Max Act: 1.8873. Min Act: -0.0001

Data Index: 61007 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 3.2956. Min Range: -3.2956

Max Act: 1.9235. Min Act: -0.0001

Data Index: 163013 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 3.2956. Min Range: -3.2956

Max Act: 1.7888. Min Act: -0.0001

Data Index: 265485 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 3.2956. Min Range: -3.2956

Max Act: 1.8601. Min Act: -0.0001

Data Index: 337446 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 3.2956. Min Range: -3.2956

Max Act: 1.8624. Min Act: -0.0001

Data Index: 938724 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 3.2956. Min Range: -3.2956

Max Act: 1.7934. Min Act: -0.0001

Data Index: 947730 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 3.2956. Min Range: -3.2956

Max Act: 1.9372. Min Act: -0.0001

Data Index: 454762 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 3.2956. Min Range: -3.2956

Max Act: 1.7377. Min Act: -0.0001

Data Index: 1038752 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 3.2956. Min Range: -3.2956

Max Act: 1.7233. Min Act: -0.0001

Data Index: 788737 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 3.2956. Min Range: -3.2956

Max Act: 1.7038. Min Act: -0.0001

Data Index: 136209 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 3.2956. Min Range: -3.2956

Max Act: 1.6344. Min Act: -0.0001

Data Index: 904225 (C4 (Web Text))

Max Activating Token Index: 503