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

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

Neuron 4639 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.2308. Min Act: -0.0000

Data Index: 725738 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.2337. Min Act: -0.0000

Data Index: 22786 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.2172. Min Act: -0.0000

Data Index: 1069723 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.2137. Min Act: -0.0000

Data Index: 1013150 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.2049. Min Act: -0.0000

Data Index: 617887 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1223151 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1922. Min Act: -0.0000

Data Index: 447595 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1960. Min Act: -0.0000

Data Index: 696500 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1971. Min Act: -0.0000

Data Index: 1333941 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1996. Min Act: -0.0000

Data Index: 1004710 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1667. Min Act: -0.0000

Data Index: 265530 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1963. Min Act: -0.0000

Data Index: 121209 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1818. Min Act: -0.0000

Data Index: 275581 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1593916 (Python Code)

Max Activating Token Index: 375

Text #14

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1925. Min Act: -0.0000

Data Index: 30047 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1121557 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1958. Min Act: -0.0000

Data Index: 1086350 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.2069. Min Act: -0.0000

Data Index: 41676 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1763. Min Act: -0.0000

Data Index: 528726 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 0.2337. Min Range: -0.2337

Max Act: 0.1791. Min Act: -0.0001

Data Index: 166388 (C4 (Web Text))

Max Activating Token Index: 55