Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 615 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.7953. Min Act: -0.0001

Data Index: 100449 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.8049. Min Act: -0.0001

Data Index: 721659 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.7629. Min Act: -0.0001

Data Index: 1201423 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6496. Min Act: -0.0001

Data Index: 1271511 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6419. Min Act: -0.0001

Data Index: 75386 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6273. Min Act: -0.0001

Data Index: 1475769 (Python Code)

Max Activating Token Index: 890

Text #6

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5841. Min Act: -0.0001

Data Index: 1587548 (Python Code)

Max Activating Token Index: 989

Text #7

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6477. Min Act: -0.0001

Data Index: 256491 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5619. Min Act: -0.0001

Data Index: 518633 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5948. Min Act: -0.0001

Data Index: 1455908 (Python Code)

Max Activating Token Index: 973

Text #10

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5288. Min Act: -0.0001

Data Index: 132811 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5899. Min Act: -0.0001

Data Index: 1462862 (Python Code)

Max Activating Token Index: 1005

Text #12

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5366. Min Act: -0.0001

Data Index: 662272 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6131. Min Act: -0.0001

Data Index: 390730 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5683. Min Act: -0.0001

Data Index: 1429998 (Python Code)

Max Activating Token Index: 213

Text #15

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5457. Min Act: -0.0001

Data Index: 1453057 (Python Code)

Max Activating Token Index: 920

Text #16

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5617. Min Act: -0.0001

Data Index: 42540 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5567. Min Act: -0.0001

Data Index: 241376 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6591. Min Act: -0.0001

Data Index: 393797 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5760. Min Act: -0.0001

Data Index: 931412 (C4 (Web Text))

Max Activating Token Index: 602