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

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

Neuron 4286 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: 2.7098. Min Range: -2.7098

Max Act: 2.6424. Min Act: -0.0000

Data Index: 278723 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 2.7098. Min Range: -2.7098

Max Act: 2.7098. Min Act: -0.0000

Data Index: 60178 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 2.7098. Min Range: -2.7098

Max Act: 2.6693. Min Act: -0.0000

Data Index: 15915 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 2.7098. Min Range: -2.7098

Max Act: 2.3991. Min Act: -0.0000

Data Index: 1289082 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 2.7098. Min Range: -2.7098

Max Act: 2.3086. Min Act: -0.0000

Data Index: 861542 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 2.7098. Min Range: -2.7098

Max Act: 2.2506. Min Act: -0.0000

Data Index: 303996 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 2.7098. Min Range: -2.7098

Max Act: 2.1892. Min Act: -0.0000

Data Index: 1094180 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 2.7098. Min Range: -2.7098

Max Act: 2.0018. Min Act: -0.0000

Data Index: 138503 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 2.7098. Min Range: -2.7098

Max Act: 2.0462. Min Act: -0.0000

Data Index: 1641935 (Python Code)

Max Activating Token Index: 879

Text #9

Max Range: 2.7098. Min Range: -2.7098

Max Act: 1.9024. Min Act: -0.0000

Data Index: 1560856 (Python Code)

Max Activating Token Index: 373

Text #10

Max Range: 2.7098. Min Range: -2.7098

Max Act: 1.8880. Min Act: -0.0000

Data Index: 1567750 (Python Code)

Max Activating Token Index: 833

Text #11

Max Range: 2.7098. Min Range: -2.7098

Max Act: 1.9873. Min Act: -0.0000

Data Index: 1408466 (Python Code)

Max Activating Token Index: 488

Text #12

Max Range: 2.7098. Min Range: -2.7098

Max Act: 1.8577. Min Act: -0.0000

Data Index: 1392346 (Python Code)

Max Activating Token Index: 118

Text #13

Max Range: 2.7098. Min Range: -2.7098

Max Act: 1.7457. Min Act: -0.0000

Data Index: 1647912 (Python Code)

Max Activating Token Index: 663

Text #14

Max Range: 2.7098. Min Range: -2.7098

Max Act: 1.7228. Min Act: -0.0000

Data Index: 460954 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 2.7098. Min Range: -2.7098

Max Act: 1.6167. Min Act: -0.0000

Data Index: 1645768 (Python Code)

Max Activating Token Index: 794

Text #16

Max Range: 2.7098. Min Range: -2.7098

Max Act: 1.6852. Min Act: -0.0000

Data Index: 320379 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 2.7098. Min Range: -2.7098

Max Act: 1.5813. Min Act: -0.0000

Data Index: 355311 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 2.7098. Min Range: -2.7098

Max Act: 1.6424. Min Act: -0.0000

Data Index: 397832 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 2.7098. Min Range: -2.7098

Max Act: 1.7414. Min Act: -0.0000

Data Index: 1403758 (Python Code)

Max Activating Token Index: 410