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

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

Neuron 580 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0998. Min Act: -0.0001

Data Index: 409820 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0963. Min Act: -0.0001

Data Index: 571467 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1243302 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0958. Min Act: -0.0001

Data Index: 848632 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0939. Min Act: -0.0001

Data Index: 22235 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0861. Min Act: -0.0001

Data Index: 862831 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0881. Min Act: -0.0001

Data Index: 1330433 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0901. Min Act: -0.0001

Data Index: 117961 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0864. Min Act: -0.0001

Data Index: 1342 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0888. Min Act: -0.0001

Data Index: 1199538 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0849. Min Act: -0.0001

Data Index: 527364 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0851. Min Act: -0.0001

Data Index: 510586 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0837. Min Act: -0.0001

Data Index: 34060 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0781. Min Act: -0.0001

Data Index: 770208 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0757. Min Act: -0.0001

Data Index: 761446 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0787. Min Act: -0.0001

Data Index: 402257 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0773. Min Act: -0.0001

Data Index: 71607 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0777. Min Act: -0.0001

Data Index: 498986 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0764. Min Act: -0.0001

Data Index: 56930 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0759. Min Act: -0.0001

Data Index: 87449 (C4 (Web Text))

Max Activating Token Index: 1022