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

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

Neuron 3560 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.7053. Min Act: -0.0000

Data Index: 1110433 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.3054. Min Act: -0.0000

Data Index: 125636 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.3796. Min Act: -0.0001

Data Index: 776446 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.1015. Min Act: -0.0001

Data Index: 833886 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.1971. Min Act: -0.0001

Data Index: 843763 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.2621. Min Act: -0.0000

Data Index: 498062 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.0646. Min Act: -0.0001

Data Index: 365954 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 1.7053. Min Range: -1.7053

Max Act: 0.9935. Min Act: -0.0001

Data Index: 746441 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.0145. Min Act: -0.0000

Data Index: 1010482 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.0220. Min Act: -0.0001

Data Index: 1019693 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.0727. Min Act: -0.0001

Data Index: 1102207 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.1691. Min Act: -0.0001

Data Index: 239113 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 1.7053. Min Range: -1.7053

Max Act: 0.9865. Min Act: -0.0001

Data Index: 996609 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 1.7053. Min Range: -1.7053

Max Act: 0.9999. Min Act: -0.0001

Data Index: 162681 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 1.7053. Min Range: -1.7053

Max Act: 0.9064. Min Act: -0.0000

Data Index: 731983 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 1.7053. Min Range: -1.7053

Max Act: 0.9492. Min Act: -0.0001

Data Index: 296419 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 1.7053. Min Range: -1.7053

Max Act: 0.9251. Min Act: -0.0001

Data Index: 93632 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 1.7053. Min Range: -1.7053

Max Act: 0.9535. Min Act: -0.0000

Data Index: 379129 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 1.7053. Min Range: -1.7053

Max Act: 0.9418. Min Act: -0.0001

Data Index: 391202 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 1.7053. Min Range: -1.7053

Max Act: 0.9718. Min Act: -0.0000

Data Index: 528904 (C4 (Web Text))

Max Activating Token Index: 87