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

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

Neuron 5803 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2091. Min Range: -2.2091

Max Act: 2.2091. Min Act: -0.0000

Data Index: 1372919 (Python Code)

Max Activating Token Index: 952

Text #1

Max Range: 2.2091. Min Range: -2.2091

Max Act: 2.1796. Min Act: -0.0000

Data Index: 1544125 (Python Code)

Max Activating Token Index: 269

Text #2

Max Range: 2.2091. Min Range: -2.2091

Max Act: 1.9605. Min Act: -0.0000

Data Index: 1382029 (Python Code)

Max Activating Token Index: 81

Text #3

Max Range: 2.2091. Min Range: -2.2091

Max Act: 1.8706. Min Act: -0.0000

Data Index: 1557647 (Python Code)

Max Activating Token Index: 203

Text #4

Max Range: 2.2091. Min Range: -2.2091

Max Act: 1.7238. Min Act: -0.0000

Data Index: 1360910 (Python Code)

Max Activating Token Index: 240

Text #5

Max Range: 2.2091. Min Range: -2.2091

Max Act: 1.8137. Min Act: -0.0000

Data Index: 1449452 (Python Code)

Max Activating Token Index: 926

Text #6

Max Range: 2.2091. Min Range: -2.2091

Max Act: 1.7085. Min Act: -0.0000

Data Index: 1536092 (Python Code)

Max Activating Token Index: 706

Text #7

Max Range: 2.2091. Min Range: -2.2091

Max Act: 1.5944. Min Act: -0.0000

Data Index: 1399496 (Python Code)

Max Activating Token Index: 107

Text #8

Max Range: 2.2091. Min Range: -2.2091

Max Act: 1.5882. Min Act: -0.0000

Data Index: 1386797 (Python Code)

Max Activating Token Index: 756

Text #9

Max Range: 2.2091. Min Range: -2.2091

Max Act: 1.6862. Min Act: -0.0000

Data Index: 1631191 (Python Code)

Max Activating Token Index: 698

Text #10

Max Range: 2.2091. Min Range: -2.2091

Max Act: 1.6327. Min Act: -0.0000

Data Index: 1165288 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 2.2091. Min Range: -2.2091

Max Act: 1.6298. Min Act: -0.0000

Data Index: 704531 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 2.2091. Min Range: -2.2091

Max Act: 1.5158. Min Act: -0.0000

Data Index: 1428333 (Python Code)

Max Activating Token Index: 945

Text #13

Max Range: 2.2091. Min Range: -2.2091

Max Act: 1.7495. Min Act: -0.0000

Data Index: 1547185 (Python Code)

Max Activating Token Index: 989

Text #14

Max Range: 2.2091. Min Range: -2.2091

Max Act: 1.3806. Min Act: -0.0000

Data Index: 1634640 (Python Code)

Max Activating Token Index: 1002

Text #15

Max Range: 2.2091. Min Range: -2.2091

Max Act: 1.6218. Min Act: -0.0000

Data Index: 1466876 (Python Code)

Max Activating Token Index: 215

Text #16

Max Range: 2.2091. Min Range: -2.2091

Max Act: 1.5243. Min Act: -0.0000

Data Index: 670183 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 2.2091. Min Range: -2.2091

Max Act: 1.4359. Min Act: -0.0000

Data Index: 1628506 (Python Code)

Max Activating Token Index: 340

Text #18

Max Range: 2.2091. Min Range: -2.2091

Max Act: 1.5025. Min Act: -0.0000

Data Index: 1152295 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 2.2091. Min Range: -2.2091

Max Act: 1.4429. Min Act: -0.0000

Data Index: 1493180 (Python Code)

Max Activating Token Index: 404