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

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

Neuron 1048 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: 11.0782. Min Range: -11.0782

Max Act: 11.0782. Min Act: -0.0001

Data Index: 110363 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 11.0782. Min Range: -11.0782

Max Act: 10.9120. Min Act: -0.0001

Data Index: 896511 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 11.0782. Min Range: -11.0782

Max Act: 8.1233. Min Act: -0.0001

Data Index: 491539 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 11.0782. Min Range: -11.0782

Max Act: 7.3984. Min Act: -0.0001

Data Index: 1337664 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 11.0782. Min Range: -11.0782

Max Act: 7.4356. Min Act: -0.0001

Data Index: 932284 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 11.0782. Min Range: -11.0782

Max Act: 7.4924. Min Act: -0.0001

Data Index: 90901 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 11.0782. Min Range: -11.0782

Max Act: 6.9140. Min Act: -0.0001

Data Index: 1184 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 11.0782. Min Range: -11.0782

Max Act: 7.3882. Min Act: -0.0001

Data Index: 865127 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 11.0782. Min Range: -11.0782

Max Act: 7.4205. Min Act: -0.0001

Data Index: 1346034 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 11.0782. Min Range: -11.0782

Max Act: 6.6590. Min Act: -0.0001

Data Index: 615328 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 11.0782. Min Range: -11.0782

Max Act: 6.6305. Min Act: -0.0001

Data Index: 457143 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 11.0782. Min Range: -11.0782

Max Act: 6.4078. Min Act: -0.0001

Data Index: 1313158 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 11.0782. Min Range: -11.0782

Max Act: 7.2439. Min Act: -0.0001

Data Index: 293169 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 11.0782. Min Range: -11.0782

Max Act: 6.8334. Min Act: -0.0001

Data Index: 69436 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 11.0782. Min Range: -11.0782

Max Act: 5.7408. Min Act: -0.0001

Data Index: 1319588 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 11.0782. Min Range: -11.0782

Max Act: 6.1984. Min Act: -0.0001

Data Index: 382816 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 11.0782. Min Range: -11.0782

Max Act: 6.1811. Min Act: -0.0001

Data Index: 992660 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 11.0782. Min Range: -11.0782

Max Act: 5.9580. Min Act: -0.0001

Data Index: 81959 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 11.0782. Min Range: -11.0782

Max Act: 6.1484. Min Act: -0.0001

Data Index: 1059036 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 11.0782. Min Range: -11.0782

Max Act: 6.1511. Min Act: -0.0001

Data Index: 935795 (C4 (Web Text))

Max Activating Token Index: 657