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

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

Neuron 3739 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: 1.2803. Min Range: -1.2803

Max Act: 1.2803. Min Act: -0.0000

Data Index: 417193 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 1.2803. Min Range: -1.2803

Max Act: 1.2189. Min Act: -0.0000

Data Index: 646092 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 1.2803. Min Range: -1.2803

Max Act: 1.2198. Min Act: -0.0000

Data Index: 874959 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 1.2803. Min Range: -1.2803

Max Act: 1.0192. Min Act: -0.0000

Data Index: 445731 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 1.2803. Min Range: -1.2803

Max Act: 1.0428. Min Act: -0.0000

Data Index: 862828 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1054192 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.9374. Min Act: -0.0000

Data Index: 331413 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.9545. Min Act: -0.0000

Data Index: 57847 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.9268. Min Act: -0.0000

Data Index: 68109 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.9283. Min Act: -0.0000

Data Index: 141372 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.8655. Min Act: -0.0000

Data Index: 1124828 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.9409. Min Act: -0.0000

Data Index: 1252928 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.8702. Min Act: -0.0000

Data Index: 641461 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.8874. Min Act: -0.0000

Data Index: 386369 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.8596. Min Act: -0.0000

Data Index: 1204032 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.8623. Min Act: -0.0000

Data Index: 906134 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.8220. Min Act: -0.0000

Data Index: 898830 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1357574 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.8205. Min Act: -0.0000

Data Index: 1290 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 1.2803. Min Range: -1.2803

Max Act: 0.8411. Min Act: -0.0000

Data Index: 7105 (C4 (Web Text))

Max Activating Token Index: 592