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

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

Neuron 4020 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2807. Min Range: -1.2807

Max Act: 1.2807. Min Act: -0.0000

Data Index: 932839 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.7258. Min Act: -0.0000

Data Index: 1571296 (Python Code)

Max Activating Token Index: 964

Text #2

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.6986. Min Act: -0.0000

Data Index: 379278 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.7177. Min Act: -0.0000

Data Index: 1546416 (Python Code)

Max Activating Token Index: 888

Text #4

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.5560. Min Act: -0.0000

Data Index: 226977 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1563673 (Python Code)

Max Activating Token Index: 684

Text #6

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.5933. Min Act: -0.0000

Data Index: 1645531 (Python Code)

Max Activating Token Index: 591

Text #7

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1474597 (Python Code)

Max Activating Token Index: 553

Text #8

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.5295. Min Act: -0.0000

Data Index: 285599 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.5193. Min Act: -0.0000

Data Index: 1520656 (Python Code)

Max Activating Token Index: 977

Text #10

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.4829. Min Act: -0.0000

Data Index: 446183 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.5614. Min Act: -0.0000

Data Index: 1375401 (Python Code)

Max Activating Token Index: 115

Text #12

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.5607. Min Act: -0.0000

Data Index: 762419 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1217273 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1454540 (Python Code)

Max Activating Token Index: 759

Text #15

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1043610 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.4631. Min Act: -0.0000

Data Index: 533102 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.4933. Min Act: -0.0000

Data Index: 32536 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.4695. Min Act: -0.0000

Data Index: 887355 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 1.2807. Min Range: -1.2807

Max Act: 0.3939. Min Act: -0.0000

Data Index: 1602506 (Python Code)

Max Activating Token Index: 210