Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 304 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.8244. Min Range: -5.8244

Max Act: 5.8244. Min Act: -0.0000

Data Index: 205725 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 5.8244. Min Range: -5.8244

Max Act: 5.7734. Min Act: -0.0000

Data Index: 996497 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 5.8244. Min Range: -5.8244

Max Act: 5.2028. Min Act: -0.0000

Data Index: 128934 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 5.8244. Min Range: -5.8244

Max Act: 5.4931. Min Act: -0.0000

Data Index: 664379 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 5.8244. Min Range: -5.8244

Max Act: 5.2666. Min Act: -0.0000

Data Index: 13133 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 5.8244. Min Range: -5.8244

Max Act: 4.5582. Min Act: -0.0000

Data Index: 920654 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 5.8244. Min Range: -5.8244

Max Act: 5.3491. Min Act: -0.0000

Data Index: 1042453 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 5.8244. Min Range: -5.8244

Max Act: 5.3391. Min Act: -0.0000

Data Index: 413099 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 5.8244. Min Range: -5.8244

Max Act: 5.5022. Min Act: -0.0000

Data Index: 81414 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 5.8244. Min Range: -5.8244

Max Act: 5.1436. Min Act: -0.0000

Data Index: 841490 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 5.8244. Min Range: -5.8244

Max Act: 4.9681. Min Act: -0.0000

Data Index: 815533 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 5.8244. Min Range: -5.8244

Max Act: 5.1001. Min Act: -0.0000

Data Index: 845581 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 5.8244. Min Range: -5.8244

Max Act: 4.8643. Min Act: -0.0000

Data Index: 185074 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 5.8244. Min Range: -5.8244

Max Act: 4.9022. Min Act: -0.0000

Data Index: 154655 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 5.8244. Min Range: -5.8244

Max Act: 5.2605. Min Act: -0.0000

Data Index: 968863 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 5.8244. Min Range: -5.8244

Max Act: 5.2179. Min Act: -0.0000

Data Index: 79259 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 5.8244. Min Range: -5.8244

Max Act: 5.1464. Min Act: -0.0000

Data Index: 545327 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 5.8244. Min Range: -5.8244

Max Act: 5.1479. Min Act: -0.0000

Data Index: 124191 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 5.8244. Min Range: -5.8244

Max Act: 4.7183. Min Act: -0.0000

Data Index: 101405 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 5.8244. Min Range: -5.8244

Max Act: 4.8928. Min Act: -0.0000

Data Index: 883730 (C4 (Web Text))

Max Activating Token Index: 466