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

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

Neuron 4270 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.9706. Min Act: -0.0000

Data Index: 1363942 (Python Code)

Max Activating Token Index: 192

Text #1

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.3299. Min Act: -0.0000

Data Index: 101493 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.5585. Min Act: -0.0000

Data Index: 1479931 (Python Code)

Max Activating Token Index: 178

Text #3

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.4289. Min Act: -0.0000

Data Index: 889739 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.3881. Min Act: -0.0000

Data Index: 279661 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.4820. Min Act: -0.0000

Data Index: 1527387 (Python Code)

Max Activating Token Index: 236

Text #6

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.3786. Min Act: -0.0000

Data Index: 1533801 (Python Code)

Max Activating Token Index: 125

Text #7

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.4483. Min Act: -0.0000

Data Index: 1440200 (Python Code)

Max Activating Token Index: 187

Text #8

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.3429. Min Act: -0.0000

Data Index: 591562 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.3942. Min Act: -0.0000

Data Index: 1428335 (Python Code)

Max Activating Token Index: 182

Text #10

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.3583. Min Act: -0.0000

Data Index: 1433158 (Python Code)

Max Activating Token Index: 239

Text #11

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.2600. Min Act: -0.0000

Data Index: 924385 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.3342. Min Act: -0.0000

Data Index: 1453041 (Python Code)

Max Activating Token Index: 97

Text #13

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.3479. Min Act: -0.0000

Data Index: 1603999 (Python Code)

Max Activating Token Index: 259

Text #14

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.3069. Min Act: -0.0000

Data Index: 1548336 (Python Code)

Max Activating Token Index: 207

Text #15

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.3654. Min Act: -0.0000

Data Index: 1545471 (Python Code)

Max Activating Token Index: 643

Text #16

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.2433. Min Act: -0.0000

Data Index: 1350443 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.2599. Min Act: -0.0000

Data Index: 106817 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.3189. Min Act: -0.0000

Data Index: 1384418 (Python Code)

Max Activating Token Index: 103

Text #19

Max Range: 1.9706. Min Range: -1.9706

Max Act: 1.1782. Min Act: -0.0000

Data Index: 1639766 (Python Code)

Max Activating Token Index: 253