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

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

Neuron 4412 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2505. Min Act: -0.0002

Data Index: 407109 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2305. Min Act: -0.0002

Data Index: 456792 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2252. Min Act: -0.0002

Data Index: 478693 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2213. Min Act: -0.0002

Data Index: 310332 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2050. Min Act: -0.0002

Data Index: 1344163 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2076. Min Act: -0.0002

Data Index: 626295 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2070. Min Act: -0.0002

Data Index: 1003283 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1954. Min Act: -0.0002

Data Index: 1264362 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1951. Min Act: -0.0002

Data Index: 751235 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1962. Min Act: -0.0002

Data Index: 272081 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1972. Min Act: -0.0002

Data Index: 1103661 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1932. Min Act: -0.0002

Data Index: 951008 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1895. Min Act: -0.0002

Data Index: 816801 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1885. Min Act: -0.0002

Data Index: 912752 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1861. Min Act: -0.0002

Data Index: 413237 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1932. Min Act: -0.0002

Data Index: 730615 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1897. Min Act: -0.0002

Data Index: 380828 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1835. Min Act: -0.0002

Data Index: 327096 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1821. Min Act: -0.0002

Data Index: 84295 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1948. Min Act: -0.0002

Data Index: 181591 (C4 (Web Text))

Max Activating Token Index: 735