Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2895 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.8675. Min Act: -0.0001

Data Index: 1073167 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.7213. Min Act: -0.0001

Data Index: 1488042 (Python Code)

Max Activating Token Index: 20

Text #2

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.6125. Min Act: -0.0001

Data Index: 1365130 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.6546. Min Act: -0.0001

Data Index: 690105 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.4128. Min Act: -0.0001

Data Index: 1136202 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.4934. Min Act: -0.0001

Data Index: 1370279 (Python Code)

Max Activating Token Index: 245

Text #6

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.4750. Min Act: -0.0001

Data Index: 15391 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.4500. Min Act: -0.0001

Data Index: 1414362 (Python Code)

Max Activating Token Index: 162

Text #8

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.4128. Min Act: -0.0001

Data Index: 1645483 (Python Code)

Max Activating Token Index: 209

Text #9

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.3026. Min Act: -0.0001

Data Index: 1581604 (Python Code)

Max Activating Token Index: 755

Text #10

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.3939. Min Act: -0.0001

Data Index: 1541700 (Python Code)

Max Activating Token Index: 466

Text #11

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.4310. Min Act: -0.0001

Data Index: 1362402 (Python Code)

Max Activating Token Index: 299

Text #12

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.2306. Min Act: -0.0001

Data Index: 459963 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.3461. Min Act: -0.0001

Data Index: 1522932 (Python Code)

Max Activating Token Index: 582

Text #14

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.3717. Min Act: -0.0001

Data Index: 1272916 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.3641. Min Act: -0.0001

Data Index: 1519856 (Python Code)

Max Activating Token Index: 336

Text #16

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.3733. Min Act: -0.0001

Data Index: 218024 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.3593. Min Act: -0.0001

Data Index: 1586862 (Python Code)

Max Activating Token Index: 449

Text #18

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.3415. Min Act: -0.0001

Data Index: 1631972 (Python Code)

Max Activating Token Index: 728

Text #19

Max Range: 1.8675. Min Range: -1.8675

Max Act: 1.3471. Min Act: -0.0001

Data Index: 378633 (C4 (Web Text))

Max Activating Token Index: 105