Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 439 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.6545. Min Act: -0.0000

Data Index: 259207 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.5681. Min Act: -0.0000

Data Index: 511162 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.6159. Min Act: -0.0000

Data Index: 803791 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.5075. Min Act: -0.0000

Data Index: 197225 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.5077. Min Act: -0.0001

Data Index: 1112675 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.5260. Min Act: -0.0000

Data Index: 616638 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1081805 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4851. Min Act: -0.0001

Data Index: 1024947 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4821. Min Act: -0.0001

Data Index: 312413 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.3993. Min Act: -0.0001

Data Index: 1408540 (Python Code)

Max Activating Token Index: 584

Text #10

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.3848. Min Act: -0.0001

Data Index: 1366585 (Python Code)

Max Activating Token Index: 321

Text #11

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.3760. Min Act: -0.0001

Data Index: 1513143 (Python Code)

Max Activating Token Index: 318

Text #12

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.3851. Min Act: -0.0001

Data Index: 565914 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1038019 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.3775. Min Act: -0.0000

Data Index: 441041 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.3552. Min Act: -0.0001

Data Index: 1411234 (Python Code)

Max Activating Token Index: 539

Text #16

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.3557. Min Act: -0.0000

Data Index: 274906 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.3520. Min Act: -0.0000

Data Index: 738303 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.3563. Min Act: -0.0000

Data Index: 472613 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.3438. Min Act: -0.0001

Data Index: 1542567 (Python Code)

Max Activating Token Index: 225