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

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

Neuron 5364 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.3419. Min Act: -0.0000

Data Index: 366020 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.3153. Min Act: -0.0000

Data Index: 578472 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.2948. Min Act: -0.0000

Data Index: 1291910 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.2918. Min Act: -0.0000

Data Index: 1009086 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.2782. Min Act: -0.0000

Data Index: 400490 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1117786 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.2869. Min Act: -0.0000

Data Index: 945581 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.2688. Min Act: -0.0000

Data Index: 572508 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.2582. Min Act: -0.0000

Data Index: 401074 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.2601. Min Act: -0.0000

Data Index: 957470 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.2638. Min Act: -0.0000

Data Index: 1040367 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.2449. Min Act: -0.0000

Data Index: 920308 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.2586. Min Act: -0.0000

Data Index: 863557 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.2543. Min Act: -0.0000

Data Index: 390477 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.2385. Min Act: -0.0000

Data Index: 534746 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.2440. Min Act: -0.0000

Data Index: 311715 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.2268. Min Act: 0.0000

Data Index: 1313089 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.2338. Min Act: -0.0000

Data Index: 612431 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.2228. Min Act: -0.0000

Data Index: 622148 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 0.3419. Min Range: -0.3419

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1302829 (C4 (Web Text))

Max Activating Token Index: 903