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

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

Neuron 1755 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: 1.2831. Min Range: -1.2831

Max Act: 1.2831. Min Act: -0.0000

Data Index: 1113781 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.1478. Min Act: -0.0000

Data Index: 760075 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.1207. Min Act: -0.0000

Data Index: 951709 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.1634. Min Act: -0.0000

Data Index: 154276 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.0188. Min Act: -0.0000

Data Index: 699525 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9678. Min Act: -0.0000

Data Index: 331121 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9962. Min Act: -0.0000

Data Index: 1138120 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9319. Min Act: -0.0000

Data Index: 529058 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9215. Min Act: -0.0000

Data Index: 193226 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.0224. Min Act: -0.0000

Data Index: 390613 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9674. Min Act: -0.0000

Data Index: 711556 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.8671. Min Act: -0.0000

Data Index: 1159582 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9178. Min Act: -0.0000

Data Index: 818518 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.8413. Min Act: -0.0000

Data Index: 29066 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1248210 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.8338. Min Act: -0.0000

Data Index: 156940 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.9410. Min Act: -0.0000

Data Index: 500315 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.8820. Min Act: -0.0000

Data Index: 425411 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.8526. Min Act: -0.0000

Data Index: 799518 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 1.2831. Min Range: -1.2831

Max Act: 0.8831. Min Act: -0.0000

Data Index: 678032 (C4 (Web Text))

Max Activating Token Index: 420