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

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

Neuron 1035 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: 3.5800. Min Range: -3.5800

Max Act: 3.5800. Min Act: -0.0000

Data Index: 1541009 (Python Code)

Max Activating Token Index: 578

Text #1

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.5316. Min Act: -0.0000

Data Index: 1509273 (Python Code)

Max Activating Token Index: 298

Text #2

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.3825. Min Act: -0.0000

Data Index: 1646221 (Python Code)

Max Activating Token Index: 501

Text #3

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.2757. Min Act: -0.0000

Data Index: 1427207 (Python Code)

Max Activating Token Index: 105

Text #4

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.0056. Min Act: -0.0000

Data Index: 1374696 (Python Code)

Max Activating Token Index: 173

Text #5

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.9495. Min Act: -0.0000

Data Index: 1555183 (Python Code)

Max Activating Token Index: 171

Text #6

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.9270. Min Act: -0.0000

Data Index: 1556502 (Python Code)

Max Activating Token Index: 535

Text #7

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.8861. Min Act: -0.0000

Data Index: 1429194 (Python Code)

Max Activating Token Index: 50

Text #8

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.8728. Min Act: -0.0000

Data Index: 1367392 (Python Code)

Max Activating Token Index: 551

Text #9

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.6303. Min Act: -0.0000

Data Index: 1454889 (Python Code)

Max Activating Token Index: 676

Text #10

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.4630. Min Act: -0.0000

Data Index: 1360734 (Python Code)

Max Activating Token Index: 251

Text #11

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.5476. Min Act: -0.0000

Data Index: 1415339 (Python Code)

Max Activating Token Index: 174

Text #12

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.5202. Min Act: -0.0000

Data Index: 1497586 (Python Code)

Max Activating Token Index: 231

Text #13

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.5174. Min Act: -0.0000

Data Index: 1461045 (Python Code)

Max Activating Token Index: 857

Text #14

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.4954. Min Act: -0.0000

Data Index: 1393222 (Python Code)

Max Activating Token Index: 201

Text #15

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.4833. Min Act: -0.0000

Data Index: 1388782 (Python Code)

Max Activating Token Index: 707

Text #16

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.4327. Min Act: -0.0000

Data Index: 1439044 (Python Code)

Max Activating Token Index: 467

Text #17

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.4460. Min Act: -0.0000

Data Index: 1531339 (Python Code)

Max Activating Token Index: 109

Text #18

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.5337. Min Act: -0.0000

Data Index: 1385339 (Python Code)

Max Activating Token Index: 70

Text #19

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.2927. Min Act: -0.0000

Data Index: 1388223 (Python Code)

Max Activating Token Index: 544