Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3949 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3767. Min Act: -0.0002

Data Index: 970788 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3535. Min Act: -0.0002

Data Index: 1003549 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3520. Min Act: -0.0001

Data Index: 434136 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3200. Min Act: -0.0001

Data Index: 1040284 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3223. Min Act: -0.0002

Data Index: 390263 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3636. Min Act: -0.0002

Data Index: 527039 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3533. Min Act: -0.0001

Data Index: 293695 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2916. Min Act: -0.0002

Data Index: 343381 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2911. Min Act: -0.0002

Data Index: 1350697 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2686. Min Act: -0.0001

Data Index: 382814 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.3172. Min Act: -0.0002

Data Index: 166710 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2960. Min Act: -0.0002

Data Index: 917294 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2966. Min Act: -0.0001

Data Index: 1005070 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2964. Min Act: -0.0002

Data Index: 51103 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2913. Min Act: -0.0001

Data Index: 576965 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2960. Min Act: -0.0002

Data Index: 1038909 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2835. Min Act: -0.0002

Data Index: 837999 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2739. Min Act: -0.0002

Data Index: 438318 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2642. Min Act: -0.0001

Data Index: 301859 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.3767. Min Range: -0.3767

Max Act: 0.2730. Min Act: -0.0002

Data Index: 963713 (C4 (Web Text))

Max Activating Token Index: 559