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

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

Neuron 986 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 9.8540. Min Range: -9.8540

Max Act: 9.8540. Min Act: -0.0000

Data Index: 1084149 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 9.8540. Min Range: -9.8540

Max Act: 8.3943. Min Act: -0.0000

Data Index: 546853 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 9.8540. Min Range: -9.8540

Max Act: 7.9050. Min Act: -0.0000

Data Index: 549448 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 9.8540. Min Range: -9.8540

Max Act: 7.8479. Min Act: -0.0000

Data Index: 728754 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 9.8540. Min Range: -9.8540

Max Act: 7.5646. Min Act: -0.0000

Data Index: 1349760 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 9.8540. Min Range: -9.8540

Max Act: 7.0229. Min Act: -0.0000

Data Index: 1237756 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 9.8540. Min Range: -9.8540

Max Act: 7.2109. Min Act: -0.0000

Data Index: 1050273 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 9.8540. Min Range: -9.8540

Max Act: 7.0121. Min Act: -0.0000

Data Index: 477932 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 9.8540. Min Range: -9.8540

Max Act: 7.3420. Min Act: -0.0000

Data Index: 477635 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 9.8540. Min Range: -9.8540

Max Act: 6.7070. Min Act: -0.0000

Data Index: 668828 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 9.8540. Min Range: -9.8540

Max Act: 6.8447. Min Act: -0.0000

Data Index: 994052 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 9.8540. Min Range: -9.8540

Max Act: 6.2146. Min Act: -0.0000

Data Index: 524556 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 9.8540. Min Range: -9.8540

Max Act: 6.3473. Min Act: -0.0000

Data Index: 477766 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 9.8540. Min Range: -9.8540

Max Act: 6.2288. Min Act: -0.0000

Data Index: 327621 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 9.8540. Min Range: -9.8540

Max Act: 6.5890. Min Act: -0.0000

Data Index: 1262412 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 9.8540. Min Range: -9.8540

Max Act: 6.3789. Min Act: -0.0000

Data Index: 1354288 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 9.8540. Min Range: -9.8540

Max Act: 5.9688. Min Act: -0.0000

Data Index: 1242491 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 9.8540. Min Range: -9.8540

Max Act: 7.2277. Min Act: -0.0000

Data Index: 358766 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 9.8540. Min Range: -9.8540

Max Act: 6.0944. Min Act: -0.0000

Data Index: 476970 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 9.8540. Min Range: -9.8540

Max Act: 6.0394. Min Act: -0.0000

Data Index: 1011570 (C4 (Web Text))

Max Activating Token Index: 165