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

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

Neuron 4325 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3141. Min Range: -1.3141

Max Act: 1.3141. Min Act: -0.0000

Data Index: 298801 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 1.3141. Min Range: -1.3141

Max Act: 1.1875. Min Act: -0.0000

Data Index: 268696 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 1.3141. Min Range: -1.3141

Max Act: 1.0627. Min Act: -0.0000

Data Index: 232669 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 1.3141. Min Range: -1.3141

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1228603 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 1.3141. Min Range: -1.3141

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1218835 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 1.3141. Min Range: -1.3141

Max Act: 0.8267. Min Act: -0.0000

Data Index: 1142965 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 1.3141. Min Range: -1.3141

Max Act: 0.7536. Min Act: -0.0000

Data Index: 231439 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 1.3141. Min Range: -1.3141

Max Act: 0.7365. Min Act: -0.0000

Data Index: 120274 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 1.3141. Min Range: -1.3141

Max Act: 0.7337. Min Act: -0.0000

Data Index: 822225 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 1.3141. Min Range: -1.3141

Max Act: 0.7038. Min Act: -0.0000

Data Index: 418419 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 1.3141. Min Range: -1.3141

Max Act: 0.6608. Min Act: -0.0000

Data Index: 441799 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 1.3141. Min Range: -1.3141

Max Act: 0.6076. Min Act: -0.0000

Data Index: 248448 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 1.3141. Min Range: -1.3141

Max Act: 0.5916. Min Act: -0.0000

Data Index: 1491846 (Python Code)

Max Activating Token Index: 985

Text #13

Max Range: 1.3141. Min Range: -1.3141

Max Act: 0.6272. Min Act: -0.0000

Data Index: 917060 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 1.3141. Min Range: -1.3141

Max Act: 0.5767. Min Act: -0.0000

Data Index: 1555102 (Python Code)

Max Activating Token Index: 571

Text #15

Max Range: 1.3141. Min Range: -1.3141

Max Act: 0.5897. Min Act: -0.0000

Data Index: 652467 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 1.3141. Min Range: -1.3141

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1019258 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 1.3141. Min Range: -1.3141

Max Act: 0.5585. Min Act: -0.0000

Data Index: 197766 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 1.3141. Min Range: -1.3141

Max Act: 0.5089. Min Act: -0.0000

Data Index: 163627 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 1.3141. Min Range: -1.3141

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1311492 (C4 (Web Text))

Max Activating Token Index: 422