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

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

Neuron 3703 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7991. Min Range: -7.7991

Max Act: 7.7991. Min Act: -0.0001

Data Index: 1284988 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 7.7991. Min Range: -7.7991

Max Act: 7.2662. Min Act: -0.0001

Data Index: 394842 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 7.7991. Min Range: -7.7991

Max Act: 5.8931. Min Act: -0.0001

Data Index: 719645 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 7.7991. Min Range: -7.7991

Max Act: 6.3139. Min Act: -0.0001

Data Index: 375084 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 7.7991. Min Range: -7.7991

Max Act: 6.1819. Min Act: -0.0001

Data Index: 433612 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 7.7991. Min Range: -7.7991

Max Act: 7.0327. Min Act: -0.0001

Data Index: 152130 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 7.7991. Min Range: -7.7991

Max Act: 6.3396. Min Act: -0.0001

Data Index: 1178808 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 7.7991. Min Range: -7.7991

Max Act: 6.0146. Min Act: -0.0001

Data Index: 1082888 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 7.7991. Min Range: -7.7991

Max Act: 6.3117. Min Act: -0.0001

Data Index: 804072 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 7.7991. Min Range: -7.7991

Max Act: 6.0525. Min Act: -0.0001

Data Index: 849082 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 7.7991. Min Range: -7.7991

Max Act: 6.2338. Min Act: -0.0001

Data Index: 125195 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 7.7991. Min Range: -7.7991

Max Act: 6.0323. Min Act: -0.0001

Data Index: 549469 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 7.7991. Min Range: -7.7991

Max Act: 6.2167. Min Act: -0.0001

Data Index: 716253 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 7.7991. Min Range: -7.7991

Max Act: 5.8630. Min Act: -0.0001

Data Index: 535628 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 7.7991. Min Range: -7.7991

Max Act: 5.7936. Min Act: -0.0001

Data Index: 700548 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 7.7991. Min Range: -7.7991

Max Act: 5.5868. Min Act: -0.0001

Data Index: 891262 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 7.7991. Min Range: -7.7991

Max Act: 5.7311. Min Act: -0.0001

Data Index: 704653 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 7.7991. Min Range: -7.7991

Max Act: 5.5459. Min Act: -0.0001

Data Index: 919020 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 7.7991. Min Range: -7.7991

Max Act: 5.5189. Min Act: -0.0001

Data Index: 801243 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 7.7991. Min Range: -7.7991

Max Act: 5.7336. Min Act: -0.0001

Data Index: 23460 (C4 (Web Text))

Max Activating Token Index: 12