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

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

Neuron 1926 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.5539. Min Act: -0.0000

Data Index: 875236 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.4930. Min Act: -0.0000

Data Index: 530738 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.2562. Min Act: -0.0000

Data Index: 1647012 (Python Code)

Max Activating Token Index: 491

Text #3

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.1293. Min Act: -0.0000

Data Index: 1444044 (Python Code)

Max Activating Token Index: 629

Text #4

Max Range: 1.5539. Min Range: -1.5539

Max Act: 1.0636. Min Act: -0.0000

Data Index: 1586099 (Python Code)

Max Activating Token Index: 724

Text #5

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.9846. Min Act: -0.0000

Data Index: 1079757 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1361431 (Python Code)

Max Activating Token Index: 431

Text #7

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.9400. Min Act: -0.0000

Data Index: 1440784 (Python Code)

Max Activating Token Index: 134

Text #8

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.8114. Min Act: -0.0000

Data Index: 1527260 (Python Code)

Max Activating Token Index: 77

Text #9

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.8737. Min Act: -0.0000

Data Index: 1411179 (Python Code)

Max Activating Token Index: 719

Text #10

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.7716. Min Act: -0.0000

Data Index: 1476747 (Python Code)

Max Activating Token Index: 386

Text #11

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1220221 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.8039. Min Act: -0.0000

Data Index: 1630416 (Python Code)

Max Activating Token Index: 637

Text #13

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.8874. Min Act: -0.0000

Data Index: 1182774 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.8249. Min Act: -0.0000

Data Index: 897967 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1406121 (Python Code)

Max Activating Token Index: 39

Text #16

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.7900. Min Act: -0.0000

Data Index: 1089416 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.8102. Min Act: -0.0000

Data Index: 20351 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.7190. Min Act: -0.0000

Data Index: 129063 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 1.5539. Min Range: -1.5539

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1640677 (Python Code)

Max Activating Token Index: 781