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

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

Neuron 745 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.5069. Min Act: -0.0000

Data Index: 1569800 (Python Code)

Max Activating Token Index: 291

Text #1

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.6310. Min Act: -0.0000

Data Index: 1361841 (Python Code)

Max Activating Token Index: 104

Text #2

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.4090. Min Act: 0.0001

Data Index: 1488551 (Python Code)

Max Activating Token Index: 695

Text #3

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.3606. Min Act: 0.0000

Data Index: 1408204 (Python Code)

Max Activating Token Index: 100

Text #4

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.4421. Min Act: -0.0000

Data Index: 1596626 (Python Code)

Max Activating Token Index: 250

Text #5

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.2579. Min Act: -0.0000

Data Index: 1498288 (Python Code)

Max Activating Token Index: 732

Text #6

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.2424. Min Act: -0.0000

Data Index: 1606613 (Python Code)

Max Activating Token Index: 246

Text #7

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.3130. Min Act: -0.0000

Data Index: 1652071 (Python Code)

Max Activating Token Index: 508

Text #8

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.2666. Min Act: -0.0000

Data Index: 1400381 (Python Code)

Max Activating Token Index: 578

Text #9

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.2814. Min Act: -0.0000

Data Index: 1654117 (Python Code)

Max Activating Token Index: 295

Text #10

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.2410. Min Act: -0.0000

Data Index: 1562665 (Python Code)

Max Activating Token Index: 336

Text #11

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.2440. Min Act: -0.0000

Data Index: 1610465 (Python Code)

Max Activating Token Index: 95

Text #12

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.0988. Min Act: 0.0000

Data Index: 1450781 (Python Code)

Max Activating Token Index: 960

Text #13

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.1548. Min Act: -0.0000

Data Index: 1465687 (Python Code)

Max Activating Token Index: 143

Text #14

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.2406. Min Act: -0.0000

Data Index: 1419229 (Python Code)

Max Activating Token Index: 239

Text #15

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.1034. Min Act: -0.0000

Data Index: 1474032 (Python Code)

Max Activating Token Index: 429

Text #16

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.0132. Min Act: -0.0000

Data Index: 1612449 (Python Code)

Max Activating Token Index: 525

Text #17

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.0735. Min Act: -0.0000

Data Index: 1570078 (Python Code)

Max Activating Token Index: 339

Text #18

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.1112. Min Act: -0.0000

Data Index: 1544262 (Python Code)

Max Activating Token Index: 457

Text #19

Max Range: 2.6310. Min Range: -2.6310

Max Act: 2.0507. Min Act: -0.0000

Data Index: 1585452 (Python Code)

Max Activating Token Index: 941