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

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

Neuron 2264 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2659. Min Range: -1.2659

Max Act: 1.2659. Min Act: -0.0000

Data Index: 828684 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 1.2659. Min Range: -1.2659

Max Act: 1.1750. Min Act: -0.0000

Data Index: 807782 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 1.2659. Min Range: -1.2659

Max Act: 1.1935. Min Act: -0.0000

Data Index: 307056 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 1.2659. Min Range: -1.2659

Max Act: 1.1551. Min Act: -0.0000

Data Index: 636948 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.9233. Min Act: -0.0000

Data Index: 269461 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8739. Min Act: -0.0000

Data Index: 123981 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8655. Min Act: -0.0000

Data Index: 1085500 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8711. Min Act: -0.0000

Data Index: 309628 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8515. Min Act: -0.0000

Data Index: 18427 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8366. Min Act: -0.0000

Data Index: 369101 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.7742. Min Act: -0.0000

Data Index: 374071 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8476. Min Act: -0.0000

Data Index: 820681 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8179. Min Act: -0.0000

Data Index: 396907 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8226. Min Act: -0.0000

Data Index: 198131 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8061. Min Act: -0.0000

Data Index: 937578 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.7999. Min Act: -0.0000

Data Index: 268614 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1140496 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.8243. Min Act: -0.0000

Data Index: 877907 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.7907. Min Act: -0.0000

Data Index: 459867 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 1.2659. Min Range: -1.2659

Max Act: 0.7828. Min Act: -0.0000

Data Index: 574955 (C4 (Web Text))

Max Activating Token Index: 78