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

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

Neuron 4407 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: 4.2522. Min Range: -4.2522

Max Act: 4.2522. Min Act: -0.0000

Data Index: 144945 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 4.2522. Min Range: -4.2522

Max Act: 3.9318. Min Act: -0.0000

Data Index: 1072645 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 4.2522. Min Range: -4.2522

Max Act: 4.0963. Min Act: -0.0000

Data Index: 442811 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 4.2522. Min Range: -4.2522

Max Act: 3.8699. Min Act: -0.0000

Data Index: 195440 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 4.2522. Min Range: -4.2522

Max Act: 3.8010. Min Act: -0.0000

Data Index: 1177593 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 4.2522. Min Range: -4.2522

Max Act: 3.7673. Min Act: -0.0000

Data Index: 1451036 (Python Code)

Max Activating Token Index: 793

Text #6

Max Range: 4.2522. Min Range: -4.2522

Max Act: 3.4477. Min Act: -0.0000

Data Index: 195406 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 4.2522. Min Range: -4.2522

Max Act: 3.6815. Min Act: -0.0000

Data Index: 187513 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 4.2522. Min Range: -4.2522

Max Act: 3.5654. Min Act: -0.0000

Data Index: 285585 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 4.2522. Min Range: -4.2522

Max Act: 3.4390. Min Act: -0.0000

Data Index: 1003280 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 4.2522. Min Range: -4.2522

Max Act: 3.6180. Min Act: -0.0000

Data Index: 1648023 (Python Code)

Max Activating Token Index: 750

Text #11

Max Range: 4.2522. Min Range: -4.2522

Max Act: 3.1369. Min Act: -0.0000

Data Index: 1615600 (Python Code)

Max Activating Token Index: 854

Text #12

Max Range: 4.2522. Min Range: -4.2522

Max Act: 3.0915. Min Act: -0.0000

Data Index: 773294 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 4.2522. Min Range: -4.2522

Max Act: 3.3381. Min Act: -0.0000

Data Index: 250456 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 4.2522. Min Range: -4.2522

Max Act: 3.1570. Min Act: -0.0000

Data Index: 1644721 (Python Code)

Max Activating Token Index: 428

Text #15

Max Range: 4.2522. Min Range: -4.2522

Max Act: 3.1383. Min Act: -0.0000

Data Index: 1335229 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 4.2522. Min Range: -4.2522

Max Act: 2.8893. Min Act: -0.0000

Data Index: 429495 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 4.2522. Min Range: -4.2522

Max Act: 3.1949. Min Act: -0.0000

Data Index: 300989 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 4.2522. Min Range: -4.2522

Max Act: 3.2006. Min Act: -0.0000

Data Index: 922329 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 4.2522. Min Range: -4.2522

Max Act: 3.1999. Min Act: -0.0000

Data Index: 1141304 (C4 (Web Text))

Max Activating Token Index: 883