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

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

Neuron 5114 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.8357. Min Act: -0.0000

Data Index: 1415172 (Python Code)

Max Activating Token Index: 636

Text #1

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.9096. Min Act: -0.0000

Data Index: 1454889 (Python Code)

Max Activating Token Index: 309

Text #2

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.8237. Min Act: -0.0000

Data Index: 1458918 (Python Code)

Max Activating Token Index: 287

Text #3

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.7310. Min Act: -0.0000

Data Index: 1513069 (Python Code)

Max Activating Token Index: 399

Text #4

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.7515. Min Act: -0.0000

Data Index: 1483148 (Python Code)

Max Activating Token Index: 942

Text #5

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.6231. Min Act: -0.0000

Data Index: 1380139 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.5989. Min Act: -0.0000

Data Index: 1490413 (Python Code)

Max Activating Token Index: 222

Text #7

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.5847. Min Act: -0.0000

Data Index: 1374058 (Python Code)

Max Activating Token Index: 616

Text #8

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.5657. Min Act: -0.0000

Data Index: 1448716 (Python Code)

Max Activating Token Index: 850

Text #9

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.5597. Min Act: -0.0000

Data Index: 1472268 (Python Code)

Max Activating Token Index: 61

Text #10

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.5321. Min Act: -0.0000

Data Index: 1555558 (Python Code)

Max Activating Token Index: 394

Text #11

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.5268. Min Act: -0.0000

Data Index: 1433794 (Python Code)

Max Activating Token Index: 181

Text #12

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.4958. Min Act: -0.0000

Data Index: 1616653 (Python Code)

Max Activating Token Index: 72

Text #13

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.4756. Min Act: -0.0000

Data Index: 310568 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.4433. Min Act: -0.0000

Data Index: 1436463 (Python Code)

Max Activating Token Index: 189

Text #15

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.5832. Min Act: -0.0000

Data Index: 1427755 (Python Code)

Max Activating Token Index: 122

Text #16

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.1760. Min Act: -0.0000

Data Index: 1644291 (Python Code)

Max Activating Token Index: 268

Text #17

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.3021. Min Act: -0.0000

Data Index: 1651259 (Python Code)

Max Activating Token Index: 832

Text #18

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.4089. Min Act: -0.0000

Data Index: 1564494 (Python Code)

Max Activating Token Index: 238

Text #19

Max Range: 2.9096. Min Range: -2.9096

Max Act: 2.3901. Min Act: -0.0000

Data Index: 1397231 (Python Code)

Max Activating Token Index: 33