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

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

Neuron 2210 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.5453. Min Act: -0.0001

Data Index: 1410236 (Python Code)

Max Activating Token Index: 1001

Text #1

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.5160. Min Act: -0.0001

Data Index: 212513 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.4721. Min Act: -0.0001

Data Index: 1218733 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.4676. Min Act: -0.0001

Data Index: 756478 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.4700. Min Act: -0.0001

Data Index: 1036307 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.4634. Min Act: -0.0001

Data Index: 1469927 (Python Code)

Max Activating Token Index: 996

Text #6

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.4587. Min Act: -0.0001

Data Index: 325404 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.4516. Min Act: -0.0001

Data Index: 366167 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.4563. Min Act: -0.0001

Data Index: 1146212 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.4310. Min Act: -0.0001

Data Index: 1040650 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.4146. Min Act: -0.0001

Data Index: 835459 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.4115. Min Act: -0.0001

Data Index: 447765 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.4330. Min Act: -0.0001

Data Index: 735694 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.4149. Min Act: -0.0001

Data Index: 1029690 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.4036. Min Act: -0.0001

Data Index: 601679 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.4014. Min Act: -0.0001

Data Index: 798859 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.3726. Min Act: -0.0001

Data Index: 64289 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.3917. Min Act: -0.0001

Data Index: 565313 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.3826. Min Act: -0.0001

Data Index: 989300 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.5453. Min Range: -0.5453

Max Act: 0.3830. Min Act: -0.0001

Data Index: 935475 (C4 (Web Text))

Max Activating Token Index: 818