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

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

Neuron 4938 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2956. Min Range: -1.2956

Max Act: 1.2956. Min Act: -0.0000

Data Index: 12946 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 1.2956. Min Range: -1.2956

Max Act: 1.1102. Min Act: -0.0000

Data Index: 347378 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 1.2956. Min Range: -1.2956

Max Act: 1.1884. Min Act: -0.0000

Data Index: 868221 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.9481. Min Act: -0.0000

Data Index: 192950 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.9149. Min Act: -0.0000

Data Index: 236346 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.7916. Min Act: -0.0000

Data Index: 80150 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.6869. Min Act: -0.0000

Data Index: 308198 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.7875. Min Act: -0.0000

Data Index: 462248 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.7796. Min Act: -0.0000

Data Index: 576269 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.7752. Min Act: -0.0000

Data Index: 228118 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.8349. Min Act: -0.0000

Data Index: 1078575 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.8579. Min Act: -0.0000

Data Index: 1358877 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1148342 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.7956. Min Act: -0.0000

Data Index: 936296 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.6852. Min Act: -0.0000

Data Index: 170452 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.6576. Min Act: -0.0000

Data Index: 114824 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.7549. Min Act: -0.0000

Data Index: 920318 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.6343. Min Act: -0.0000

Data Index: 157398 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.6782. Min Act: -0.0000

Data Index: 695862 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 1.2956. Min Range: -1.2956

Max Act: 0.6142. Min Act: -0.0000

Data Index: 79847 (C4 (Web Text))

Max Activating Token Index: 442