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

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

Neuron 1138 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.6753. Min Act: -0.0002

Data Index: 1293999 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.6176. Min Act: -0.0001

Data Index: 1460316 (Python Code)

Max Activating Token Index: 929

Text #2

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.6195. Min Act: -0.0002

Data Index: 1040006 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.6447. Min Act: -0.0001

Data Index: 1609992 (Python Code)

Max Activating Token Index: 94

Text #4

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.5887. Min Act: -0.0001

Data Index: 1524749 (Python Code)

Max Activating Token Index: 96

Text #5

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.6020. Min Act: -0.0001

Data Index: 1557170 (Python Code)

Max Activating Token Index: 774

Text #6

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.5686. Min Act: -0.0001

Data Index: 1360132 (Python Code)

Max Activating Token Index: 285

Text #7

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.5397. Min Act: -0.0001

Data Index: 1585663 (Python Code)

Max Activating Token Index: 940

Text #8

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.5403. Min Act: -0.0001

Data Index: 1628960 (Python Code)

Max Activating Token Index: 140

Text #9

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.5383. Min Act: -0.0002

Data Index: 597714 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.5034. Min Act: -0.0001

Data Index: 1382263 (Python Code)

Max Activating Token Index: 214

Text #11

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.5464. Min Act: -0.0001

Data Index: 1592015 (Python Code)

Max Activating Token Index: 571

Text #12

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.5169. Min Act: -0.0001

Data Index: 1457996 (Python Code)

Max Activating Token Index: 56

Text #13

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.5446. Min Act: -0.0001

Data Index: 1585163 (Python Code)

Max Activating Token Index: 816

Text #14

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.4861. Min Act: -0.0002

Data Index: 1438135 (Python Code)

Max Activating Token Index: 585

Text #15

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.5276. Min Act: -0.0001

Data Index: 546506 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.5177. Min Act: -0.0002

Data Index: 502762 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.5575. Min Act: -0.0001

Data Index: 1394490 (Python Code)

Max Activating Token Index: 637

Text #18

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.5074. Min Act: -0.0001

Data Index: 1645658 (Python Code)

Max Activating Token Index: 497

Text #19

Max Range: 0.6753. Min Range: -0.6753

Max Act: 0.5166. Min Act: -0.0001

Data Index: 51341 (C4 (Web Text))

Max Activating Token Index: 161