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

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

Neuron 2843 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2861. Min Range: -2.2861

Max Act: 2.2861. Min Act: -0.0000

Data Index: 1363877 (Python Code)

Max Activating Token Index: 212

Text #1

Max Range: 2.2861. Min Range: -2.2861

Max Act: 2.2742. Min Act: -0.0000

Data Index: 1476504 (Python Code)

Max Activating Token Index: 891

Text #2

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.6472. Min Act: -0.0000

Data Index: 1643053 (Python Code)

Max Activating Token Index: 488

Text #3

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.6461. Min Act: -0.0000

Data Index: 1416570 (Python Code)

Max Activating Token Index: 793

Text #4

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.4184. Min Act: -0.0000

Data Index: 1509685 (Python Code)

Max Activating Token Index: 712

Text #5

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.5197. Min Act: -0.0000

Data Index: 1451372 (Python Code)

Max Activating Token Index: 803

Text #6

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.6259. Min Act: -0.0000

Data Index: 1490086 (Python Code)

Max Activating Token Index: 858

Text #7

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.5307. Min Act: -0.0000

Data Index: 1399450 (Python Code)

Max Activating Token Index: 782

Text #8

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.5056. Min Act: -0.0000

Data Index: 1652640 (Python Code)

Max Activating Token Index: 669

Text #9

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.5635. Min Act: -0.0000

Data Index: 1590056 (Python Code)

Max Activating Token Index: 556

Text #10

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.5269. Min Act: -0.0000

Data Index: 1379664 (Python Code)

Max Activating Token Index: 426

Text #11

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.4991. Min Act: -0.0000

Data Index: 1422419 (Python Code)

Max Activating Token Index: 911

Text #12

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.3096. Min Act: -0.0000

Data Index: 1515844 (Python Code)

Max Activating Token Index: 361

Text #13

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.3217. Min Act: -0.0000

Data Index: 1492142 (Python Code)

Max Activating Token Index: 211

Text #14

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.3130. Min Act: -0.0000

Data Index: 1463807 (Python Code)

Max Activating Token Index: 809

Text #15

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.3040. Min Act: -0.0000

Data Index: 1391999 (Python Code)

Max Activating Token Index: 700

Text #16

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.2836. Min Act: -0.0000

Data Index: 1523235 (Python Code)

Max Activating Token Index: 273

Text #17

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.2877. Min Act: -0.0000

Data Index: 1575508 (Python Code)

Max Activating Token Index: 394

Text #18

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.2513. Min Act: -0.0000

Data Index: 1361819 (Python Code)

Max Activating Token Index: 346

Text #19

Max Range: 2.2861. Min Range: -2.2861

Max Act: 1.3520. Min Act: -0.0000

Data Index: 1489377 (Python Code)

Max Activating Token Index: 101