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

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

Neuron 2990 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: 2.4190. Min Range: -2.4190

Max Act: 2.3824. Min Act: -0.0000

Data Index: 1576463 (Python Code)

Max Activating Token Index: 885

Text #1

Max Range: 2.4190. Min Range: -2.4190

Max Act: 2.4190. Min Act: -0.0000

Data Index: 1580429 (Python Code)

Max Activating Token Index: 526

Text #2

Max Range: 2.4190. Min Range: -2.4190

Max Act: 2.1808. Min Act: -0.0000

Data Index: 1483492 (Python Code)

Max Activating Token Index: 745

Text #3

Max Range: 2.4190. Min Range: -2.4190

Max Act: 2.1580. Min Act: -0.0000

Data Index: 1383129 (Python Code)

Max Activating Token Index: 202

Text #4

Max Range: 2.4190. Min Range: -2.4190

Max Act: 2.0163. Min Act: -0.0000

Data Index: 1518557 (Python Code)

Max Activating Token Index: 41

Text #5

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.9480. Min Act: -0.0000

Data Index: 1639789 (Python Code)

Max Activating Token Index: 195

Text #6

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.9326. Min Act: -0.0000

Data Index: 1484451 (Python Code)

Max Activating Token Index: 413

Text #7

Max Range: 2.4190. Min Range: -2.4190

Max Act: 2.0018. Min Act: -0.0000

Data Index: 1505425 (Python Code)

Max Activating Token Index: 301

Text #8

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.9905. Min Act: -0.0000

Data Index: 1449290 (Python Code)

Max Activating Token Index: 295

Text #9

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.9825. Min Act: -0.0000

Data Index: 1386781 (Python Code)

Max Activating Token Index: 159

Text #10

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.8665. Min Act: -0.0000

Data Index: 1634126 (Python Code)

Max Activating Token Index: 817

Text #11

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.9856. Min Act: -0.0000

Data Index: 1554669 (Python Code)

Max Activating Token Index: 711

Text #12

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.9715. Min Act: -0.0000

Data Index: 1529894 (Python Code)

Max Activating Token Index: 185

Text #13

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.8405. Min Act: -0.0000

Data Index: 1617071 (Python Code)

Max Activating Token Index: 471

Text #14

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.9214. Min Act: -0.0000

Data Index: 1578116 (Python Code)

Max Activating Token Index: 712

Text #15

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.8142. Min Act: -0.0000

Data Index: 1429315 (Python Code)

Max Activating Token Index: 620

Text #16

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.9149. Min Act: -0.0000

Data Index: 1615644 (Python Code)

Max Activating Token Index: 768

Text #17

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.9167. Min Act: -0.0000

Data Index: 1450451 (Python Code)

Max Activating Token Index: 918

Text #18

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.9009. Min Act: -0.0000

Data Index: 1492154 (Python Code)

Max Activating Token Index: 447

Text #19

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.8017. Min Act: -0.0000

Data Index: 1598951 (Python Code)

Max Activating Token Index: 1009