Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4299 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4806. Min Act: -0.0000

Data Index: 10739 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4385. Min Act: -0.0000

Data Index: 1357779 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4122. Min Act: -0.0000

Data Index: 643349 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3887. Min Act: -0.0000

Data Index: 986092 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3990. Min Act: -0.0000

Data Index: 523484 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1040859 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3713. Min Act: -0.0000

Data Index: 182570 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3639. Min Act: -0.0000

Data Index: 635565 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1062536 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3261. Min Act: -0.0000

Data Index: 50096 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3062. Min Act: -0.0000

Data Index: 1139376 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.2947. Min Act: -0.0000

Data Index: 1498604 (Python Code)

Max Activating Token Index: 56

Text #12

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.2723. Min Act: -0.0000

Data Index: 1638122 (Python Code)

Max Activating Token Index: 599

Text #13

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3068. Min Act: -0.0000

Data Index: 381387 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.2740. Min Act: -0.0000

Data Index: 676598 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1431768 (Python Code)

Max Activating Token Index: 959

Text #16

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.2782. Min Act: -0.0000

Data Index: 1111859 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.2885. Min Act: -0.0000

Data Index: 673173 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1561929 (Python Code)

Max Activating Token Index: 969

Text #19

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.2764. Min Act: -0.0000

Data Index: 1426550 (Python Code)

Max Activating Token Index: 114