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

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

Neuron 4 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1479. Min Range: -5.1479

Max Act: 5.1479. Min Act: -0.0000

Data Index: 361014 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 5.1479. Min Range: -5.1479

Max Act: 4.7306. Min Act: -0.0001

Data Index: 1049464 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 5.1479. Min Range: -5.1479

Max Act: 4.7460. Min Act: -0.0000

Data Index: 1314911 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 5.1479. Min Range: -5.1479

Max Act: 4.7865. Min Act: -0.0001

Data Index: 270191 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 5.1479. Min Range: -5.1479

Max Act: 4.4114. Min Act: -0.0001

Data Index: 823792 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 5.1479. Min Range: -5.1479

Max Act: 4.2467. Min Act: -0.0001

Data Index: 330777 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 5.1479. Min Range: -5.1479

Max Act: 4.4546. Min Act: -0.0000

Data Index: 485163 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 5.1479. Min Range: -5.1479

Max Act: 4.1912. Min Act: -0.0001

Data Index: 566307 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 5.1479. Min Range: -5.1479

Max Act: 4.3648. Min Act: -0.0000

Data Index: 180379 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 5.1479. Min Range: -5.1479

Max Act: 4.0930. Min Act: -0.0000

Data Index: 510708 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 5.1479. Min Range: -5.1479

Max Act: 4.0677. Min Act: -0.0000

Data Index: 429342 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 5.1479. Min Range: -5.1479

Max Act: 3.8898. Min Act: -0.0000

Data Index: 93142 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 5.1479. Min Range: -5.1479

Max Act: 4.0475. Min Act: -0.0000

Data Index: 942191 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 5.1479. Min Range: -5.1479

Max Act: 4.4822. Min Act: -0.0000

Data Index: 731284 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 5.1479. Min Range: -5.1479

Max Act: 3.8362. Min Act: -0.0000

Data Index: 1141185 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 5.1479. Min Range: -5.1479

Max Act: 3.6014. Min Act: -0.0000

Data Index: 7037 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 5.1479. Min Range: -5.1479

Max Act: 3.6550. Min Act: -0.0000

Data Index: 451701 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 5.1479. Min Range: -5.1479

Max Act: 3.3296. Min Act: -0.0001

Data Index: 674152 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 5.1479. Min Range: -5.1479

Max Act: 3.2958. Min Act: -0.0001

Data Index: 1183627 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 5.1479. Min Range: -5.1479

Max Act: 3.3844. Min Act: -0.0000

Data Index: 76488 (C4 (Web Text))

Max Activating Token Index: 559