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

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

Neuron 2546 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6106. Min Range: -2.6106

Max Act: 2.6106. Min Act: -0.0000

Data Index: 805073 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 2.6106. Min Range: -2.6106

Max Act: 2.0942. Min Act: -0.0000

Data Index: 837418 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 2.6106. Min Range: -2.6106

Max Act: 1.8037. Min Act: -0.0000

Data Index: 437547 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 2.6106. Min Range: -2.6106

Max Act: 1.9368. Min Act: -0.0000

Data Index: 198243 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 2.6106. Min Range: -2.6106

Max Act: 1.7990. Min Act: -0.0000

Data Index: 754698 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 2.6106. Min Range: -2.6106

Max Act: 1.9071. Min Act: -0.0000

Data Index: 33313 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 2.6106. Min Range: -2.6106

Max Act: 1.9166. Min Act: -0.0000

Data Index: 467753 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 2.6106. Min Range: -2.6106

Max Act: 1.7735. Min Act: -0.0000

Data Index: 1396713 (Python Code)

Max Activating Token Index: 98

Text #8

Max Range: 2.6106. Min Range: -2.6106

Max Act: 1.6829. Min Act: -0.0000

Data Index: 198568 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 2.6106. Min Range: -2.6106

Max Act: 1.8506. Min Act: -0.0000

Data Index: 233590 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 2.6106. Min Range: -2.6106

Max Act: 1.8161. Min Act: -0.0000

Data Index: 1376324 (Python Code)

Max Activating Token Index: 17

Text #11

Max Range: 2.6106. Min Range: -2.6106

Max Act: 1.7192. Min Act: -0.0000

Data Index: 1600583 (Python Code)

Max Activating Token Index: 671

Text #12

Max Range: 2.6106. Min Range: -2.6106

Max Act: 1.8956. Min Act: -0.0000

Data Index: 1139238 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 2.6106. Min Range: -2.6106

Max Act: 1.6697. Min Act: -0.0000

Data Index: 1636625 (Python Code)

Max Activating Token Index: 82

Text #14

Max Range: 2.6106. Min Range: -2.6106

Max Act: 1.6613. Min Act: -0.0000

Data Index: 1535357 (Python Code)

Max Activating Token Index: 351

Text #15

Max Range: 2.6106. Min Range: -2.6106

Max Act: 1.5445. Min Act: -0.0000

Data Index: 283967 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 2.6106. Min Range: -2.6106

Max Act: 1.6439. Min Act: -0.0000

Data Index: 88643 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 2.6106. Min Range: -2.6106

Max Act: 1.7458. Min Act: -0.0000

Data Index: 1651662 (Python Code)

Max Activating Token Index: 288

Text #18

Max Range: 2.6106. Min Range: -2.6106

Max Act: 1.5428. Min Act: -0.0000

Data Index: 139316 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 2.6106. Min Range: -2.6106

Max Act: 1.6365. Min Act: -0.0000

Data Index: 748194 (C4 (Web Text))

Max Activating Token Index: 747