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

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

Neuron 4689 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: 0.5074. Min Range: -0.5074

Max Act: 0.5074. Min Act: -0.0001

Data Index: 413168 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.4915. Min Act: -0.0001

Data Index: 937609 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.4109. Min Act: -0.0001

Data Index: 1398619 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.4263. Min Act: -0.0001

Data Index: 1523521 (Python Code)

Max Activating Token Index: 966

Text #4

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3854. Min Act: -0.0001

Data Index: 1641123 (Python Code)

Max Activating Token Index: 947

Text #5

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3836. Min Act: -0.0001

Data Index: 1515180 (Python Code)

Max Activating Token Index: 153

Text #6

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3748. Min Act: -0.0001

Data Index: 1242597 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3750. Min Act: -0.0001

Data Index: 160136 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3842. Min Act: -0.0001

Data Index: 1591052 (Python Code)

Max Activating Token Index: 242

Text #9

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.4030. Min Act: -0.0001

Data Index: 715340 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3913. Min Act: -0.0001

Data Index: 1483216 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3523. Min Act: -0.0001

Data Index: 1207225 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3126. Min Act: -0.0001

Data Index: 1564409 (Python Code)

Max Activating Token Index: 833

Text #13

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3821. Min Act: -0.0001

Data Index: 1640764 (Python Code)

Max Activating Token Index: 15

Text #14

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3514. Min Act: -0.0001

Data Index: 626192 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3581. Min Act: -0.0001

Data Index: 80477 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3439. Min Act: -0.0001

Data Index: 512412 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3550. Min Act: -0.0001

Data Index: 1234395 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3467. Min Act: -0.0001

Data Index: 1559512 (Python Code)

Max Activating Token Index: 26

Text #19

Max Range: 0.5074. Min Range: -0.5074

Max Act: 0.3399. Min Act: -0.0001

Data Index: 1480956 (Python Code)

Max Activating Token Index: 596