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

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

Neuron 654 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: 1.7520. Min Range: -1.7520

Max Act: 1.7520. Min Act: -0.0000

Data Index: 754305 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 1.7520. Min Range: -1.7520

Max Act: 1.3667. Min Act: -0.0000

Data Index: 1313501 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 1.7520. Min Range: -1.7520

Max Act: 1.2277. Min Act: -0.0000

Data Index: 1145802 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 1.7520. Min Range: -1.7520

Max Act: 1.1522. Min Act: -0.0000

Data Index: 272277 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 1.7520. Min Range: -1.7520

Max Act: 1.1323. Min Act: -0.0000

Data Index: 583791 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 1.7520. Min Range: -1.7520

Max Act: 1.0311. Min Act: -0.0000

Data Index: 487814 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 1.7520. Min Range: -1.7520

Max Act: 1.0104. Min Act: -0.0000

Data Index: 564436 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 1.7520. Min Range: -1.7520

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1211496 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 1.7520. Min Range: -1.7520

Max Act: 0.9403. Min Act: -0.0000

Data Index: 428249 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 1.7520. Min Range: -1.7520

Max Act: 0.9244. Min Act: -0.0000

Data Index: 655486 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 1.7520. Min Range: -1.7520

Max Act: 0.9619. Min Act: -0.0000

Data Index: 437540 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 1.7520. Min Range: -1.7520

Max Act: 0.8313. Min Act: -0.0000

Data Index: 406233 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 1.7520. Min Range: -1.7520

Max Act: 0.8997. Min Act: -0.0000

Data Index: 625577 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 1.7520. Min Range: -1.7520

Max Act: 0.9790. Min Act: -0.0000

Data Index: 30520 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 1.7520. Min Range: -1.7520

Max Act: 0.8978. Min Act: -0.0000

Data Index: 324496 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 1.7520. Min Range: -1.7520

Max Act: 0.8364. Min Act: -0.0000

Data Index: 296853 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 1.7520. Min Range: -1.7520

Max Act: 0.8375. Min Act: -0.0000

Data Index: 835850 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 1.7520. Min Range: -1.7520

Max Act: 0.8227. Min Act: -0.0000

Data Index: 189871 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 1.7520. Min Range: -1.7520

Max Act: 0.8343. Min Act: -0.0000

Data Index: 589395 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 1.7520. Min Range: -1.7520

Max Act: 0.7991. Min Act: -0.0000

Data Index: 670822 (C4 (Web Text))

Max Activating Token Index: 154