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

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

Neuron 4335 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: 1.8873. Min Range: -1.8873

Max Act: 1.8293. Min Act: -0.0000

Data Index: 1419141 (Python Code)

Max Activating Token Index: 745

Text #1

Max Range: 1.8873. Min Range: -1.8873

Max Act: 1.8184. Min Act: -0.0000

Data Index: 287963 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 1.8873. Min Range: -1.8873

Max Act: 1.8873. Min Act: -0.0000

Data Index: 1643228 (Python Code)

Max Activating Token Index: 124

Text #3

Max Range: 1.8873. Min Range: -1.8873

Max Act: 1.6795. Min Act: -0.0000

Data Index: 776636 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 1.8873. Min Range: -1.8873

Max Act: 1.7775. Min Act: -0.0000

Data Index: 1615628 (Python Code)

Max Activating Token Index: 564

Text #5

Max Range: 1.8873. Min Range: -1.8873

Max Act: 1.7813. Min Act: -0.0000

Data Index: 1632734 (Python Code)

Max Activating Token Index: 863

Text #6

Max Range: 1.8873. Min Range: -1.8873

Max Act: 1.8515. Min Act: -0.0000

Data Index: 1575685 (Python Code)

Max Activating Token Index: 118

Text #7

Max Range: 1.8873. Min Range: -1.8873

Max Act: 1.7026. Min Act: -0.0000

Data Index: 1338651 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 1.8873. Min Range: -1.8873

Max Act: 1.6922. Min Act: -0.0000

Data Index: 1442875 (Python Code)

Max Activating Token Index: 108

Text #9

Max Range: 1.8873. Min Range: -1.8873

Max Act: 1.6932. Min Act: -0.0000

Data Index: 1096432 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 1.8873. Min Range: -1.8873

Max Act: 1.5598. Min Act: -0.0000

Data Index: 1245960 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 1.8873. Min Range: -1.8873

Max Act: 1.6588. Min Act: -0.0000

Data Index: 1310601 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 1.8873. Min Range: -1.8873

Max Act: 1.6593. Min Act: -0.0000

Data Index: 1616715 (Python Code)

Max Activating Token Index: 423

Text #13

Max Range: 1.8873. Min Range: -1.8873

Max Act: 1.6262. Min Act: -0.0000

Data Index: 280142 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 1.8873. Min Range: -1.8873

Max Act: 1.6184. Min Act: -0.0000

Data Index: 1597473 (Python Code)

Max Activating Token Index: 263

Text #15

Max Range: 1.8873. Min Range: -1.8873

Max Act: 1.6218. Min Act: -0.0000

Data Index: 1445349 (Python Code)

Max Activating Token Index: 176

Text #16

Max Range: 1.8873. Min Range: -1.8873

Max Act: 1.6158. Min Act: -0.0000

Data Index: 359345 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 1.8873. Min Range: -1.8873

Max Act: 1.6075. Min Act: -0.0000

Data Index: 580707 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 1.8873. Min Range: -1.8873

Max Act: 1.5848. Min Act: -0.0000

Data Index: 1097637 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 1.8873. Min Range: -1.8873

Max Act: 1.5954. Min Act: -0.0000

Data Index: 1525227 (Python Code)

Max Activating Token Index: 944