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

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

Neuron 565 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: 1.4236. Min Range: -1.4236

Max Act: 1.4236. Min Act: -0.0000

Data Index: 883821 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 1.4236. Min Range: -1.4236

Max Act: 1.4140. Min Act: -0.0000

Data Index: 149341 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 1.4236. Min Range: -1.4236

Max Act: 1.2831. Min Act: -0.0000

Data Index: 240781 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 1.4236. Min Range: -1.4236

Max Act: 1.1687. Min Act: -0.0000

Data Index: 1007435 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 1.4236. Min Range: -1.4236

Max Act: 1.2473. Min Act: -0.0000

Data Index: 509671 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 1.4236. Min Range: -1.4236

Max Act: 1.2373. Min Act: -0.0000

Data Index: 1336324 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 1.4236. Min Range: -1.4236

Max Act: 1.1678. Min Act: -0.0000

Data Index: 734018 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 1.4236. Min Range: -1.4236

Max Act: 1.1417. Min Act: -0.0000

Data Index: 1008243 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 1.4236. Min Range: -1.4236

Max Act: 1.0644. Min Act: -0.0000

Data Index: 409169 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.9978. Min Act: -0.0000

Data Index: 689517 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 1.4236. Min Range: -1.4236

Max Act: 1.0165. Min Act: -0.0000

Data Index: 83586 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 1.4236. Min Range: -1.4236

Max Act: 1.1227. Min Act: -0.0000

Data Index: 812215 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 1.4236. Min Range: -1.4236

Max Act: 1.0794. Min Act: -0.0000

Data Index: 172394 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.9821. Min Act: -0.0000

Data Index: 594278 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 1.4236. Min Range: -1.4236

Max Act: 1.0038. Min Act: -0.0000

Data Index: 1066807 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.9342. Min Act: -0.0000

Data Index: 404199 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 1.4236. Min Range: -1.4236

Max Act: 1.0141. Min Act: -0.0000

Data Index: 1309898 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.9575. Min Act: -0.0000

Data Index: 912495 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.8891. Min Act: -0.0000

Data Index: 149664 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 1.4236. Min Range: -1.4236

Max Act: 0.9102. Min Act: -0.0000

Data Index: 597815 (C4 (Web Text))

Max Activating Token Index: 984