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

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

Neuron 472 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3319. Min Range: -5.3319

Max Act: 5.3319. Min Act: -0.0000

Data Index: 1257507 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 5.3319. Min Range: -5.3319

Max Act: 5.0513. Min Act: -0.0000

Data Index: 42532 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 5.3319. Min Range: -5.3319

Max Act: 4.8011. Min Act: -0.0000

Data Index: 199892 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 5.3319. Min Range: -5.3319

Max Act: 4.7656. Min Act: -0.0000

Data Index: 1004124 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 5.3319. Min Range: -5.3319

Max Act: 4.4436. Min Act: -0.0000

Data Index: 205530 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 5.3319. Min Range: -5.3319

Max Act: 4.6221. Min Act: -0.0000

Data Index: 675974 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 5.3319. Min Range: -5.3319

Max Act: 4.5681. Min Act: -0.0000

Data Index: 315785 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 5.3319. Min Range: -5.3319

Max Act: 4.5553. Min Act: -0.0000

Data Index: 901069 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 5.3319. Min Range: -5.3319

Max Act: 4.7582. Min Act: -0.0000

Data Index: 784084 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 5.3319. Min Range: -5.3319

Max Act: 4.3329. Min Act: -0.0000

Data Index: 68677 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 5.3319. Min Range: -5.3319

Max Act: 4.6945. Min Act: -0.0000

Data Index: 765927 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 5.3319. Min Range: -5.3319

Max Act: 4.4472. Min Act: -0.0000

Data Index: 890469 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 5.3319. Min Range: -5.3319

Max Act: 4.4329. Min Act: -0.0000

Data Index: 1070078 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 5.3319. Min Range: -5.3319

Max Act: 4.3404. Min Act: -0.0000

Data Index: 1005309 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 5.3319. Min Range: -5.3319

Max Act: 4.2987. Min Act: -0.0000

Data Index: 345808 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 5.3319. Min Range: -5.3319

Max Act: 4.2755. Min Act: -0.0000

Data Index: 355776 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 5.3319. Min Range: -5.3319

Max Act: 4.2217. Min Act: -0.0000

Data Index: 1343936 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 5.3319. Min Range: -5.3319

Max Act: 3.9961. Min Act: -0.0000

Data Index: 901811 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 5.3319. Min Range: -5.3319

Max Act: 3.9544. Min Act: -0.0000

Data Index: 117948 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 5.3319. Min Range: -5.3319

Max Act: 4.1268. Min Act: -0.0000

Data Index: 662486 (C4 (Web Text))

Max Activating Token Index: 855