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

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

Neuron 3216 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: 1.6762. Min Range: -1.6762

Max Act: 1.5542. Min Act: -0.0001

Data Index: 503954 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 1.6762. Min Range: -1.6762

Max Act: 1.6762. Min Act: -0.0001

Data Index: 455144 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 1.6762. Min Range: -1.6762

Max Act: 1.5714. Min Act: -0.0001

Data Index: 1305020 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 1.6762. Min Range: -1.6762

Max Act: 1.3999. Min Act: -0.0001

Data Index: 209843 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 1.6762. Min Range: -1.6762

Max Act: 1.4631. Min Act: -0.0001

Data Index: 297693 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 1.6762. Min Range: -1.6762

Max Act: 1.4198. Min Act: -0.0001

Data Index: 39200 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 1.6762. Min Range: -1.6762

Max Act: 1.4027. Min Act: -0.0001

Data Index: 590241 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 1.6762. Min Range: -1.6762

Max Act: 1.3707. Min Act: -0.0001

Data Index: 261810 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 1.6762. Min Range: -1.6762

Max Act: 1.3512. Min Act: -0.0001

Data Index: 72876 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 1.6762. Min Range: -1.6762

Max Act: 1.2667. Min Act: -0.0001

Data Index: 876231 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 1.6762. Min Range: -1.6762

Max Act: 1.4050. Min Act: -0.0001

Data Index: 468111 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 1.6762. Min Range: -1.6762

Max Act: 1.3171. Min Act: -0.0001

Data Index: 919862 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 1.6762. Min Range: -1.6762

Max Act: 1.3010. Min Act: -0.0001

Data Index: 8661 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 1.6762. Min Range: -1.6762

Max Act: 1.2284. Min Act: -0.0001

Data Index: 1095490 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 1.6762. Min Range: -1.6762

Max Act: 1.3007. Min Act: -0.0001

Data Index: 687269 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 1.6762. Min Range: -1.6762

Max Act: 1.2646. Min Act: -0.0001

Data Index: 521132 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 1.6762. Min Range: -1.6762

Max Act: 1.1949. Min Act: -0.0001

Data Index: 979874 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 1.6762. Min Range: -1.6762

Max Act: 1.2288. Min Act: -0.0001

Data Index: 1261773 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 1.6762. Min Range: -1.6762

Max Act: 1.2636. Min Act: -0.0001

Data Index: 1331911 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 1.6762. Min Range: -1.6762

Max Act: 1.2979. Min Act: -0.0001

Data Index: 853588 (C4 (Web Text))

Max Activating Token Index: 943