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

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

Neuron 5815 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: 3.5479. Min Range: -3.5479

Max Act: 3.5479. Min Act: -0.0000

Data Index: 1400300 (Python Code)

Max Activating Token Index: 958

Text #1

Max Range: 3.5479. Min Range: -3.5479

Max Act: 2.6196. Min Act: -0.0000

Data Index: 1528472 (Python Code)

Max Activating Token Index: 579

Text #2

Max Range: 3.5479. Min Range: -3.5479

Max Act: 2.5638. Min Act: -0.0000

Data Index: 599734 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 3.5479. Min Range: -3.5479

Max Act: 2.5736. Min Act: -0.0000

Data Index: 426059 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 3.5479. Min Range: -3.5479

Max Act: 2.4090. Min Act: -0.0000

Data Index: 584807 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 3.5479. Min Range: -3.5479

Max Act: 2.5006. Min Act: -0.0000

Data Index: 1416358 (Python Code)

Max Activating Token Index: 1019

Text #6

Max Range: 3.5479. Min Range: -3.5479

Max Act: 2.3645. Min Act: -0.0000

Data Index: 1428019 (Python Code)

Max Activating Token Index: 699

Text #7

Max Range: 3.5479. Min Range: -3.5479

Max Act: 2.5785. Min Act: -0.0000

Data Index: 1464969 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 3.5479. Min Range: -3.5479

Max Act: 2.5376. Min Act: -0.0000

Data Index: 1583344 (Python Code)

Max Activating Token Index: 416

Text #9

Max Range: 3.5479. Min Range: -3.5479

Max Act: 2.2388. Min Act: -0.0000

Data Index: 1561092 (Python Code)

Max Activating Token Index: 146

Text #10

Max Range: 3.5479. Min Range: -3.5479

Max Act: 2.4380. Min Act: -0.0000

Data Index: 1527750 (Python Code)

Max Activating Token Index: 565

Text #11

Max Range: 3.5479. Min Range: -3.5479

Max Act: 2.3255. Min Act: -0.0000

Data Index: 1656950 (Python Code)

Max Activating Token Index: 538

Text #12

Max Range: 3.5479. Min Range: -3.5479

Max Act: 2.3117. Min Act: -0.0000

Data Index: 179142 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 3.5479. Min Range: -3.5479

Max Act: 2.2615. Min Act: -0.0000

Data Index: 1441168 (Python Code)

Max Activating Token Index: 263

Text #14

Max Range: 3.5479. Min Range: -3.5479

Max Act: 2.2889. Min Act: -0.0000

Data Index: 1533215 (Python Code)

Max Activating Token Index: 589

Text #15

Max Range: 3.5479. Min Range: -3.5479

Max Act: 2.1367. Min Act: -0.0000

Data Index: 1372273 (Python Code)

Max Activating Token Index: 991

Text #16

Max Range: 3.5479. Min Range: -3.5479

Max Act: 2.2176. Min Act: -0.0000

Data Index: 1598317 (Python Code)

Max Activating Token Index: 204

Text #17

Max Range: 3.5479. Min Range: -3.5479

Max Act: 2.2085. Min Act: -0.0000

Data Index: 1536156 (Python Code)

Max Activating Token Index: 43

Text #18

Max Range: 3.5479. Min Range: -3.5479

Max Act: 2.0899. Min Act: -0.0000

Data Index: 318224 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 3.5479. Min Range: -3.5479

Max Act: 2.1932. Min Act: -0.0000

Data Index: 347987 (C4 (Web Text))

Max Activating Token Index: 142