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

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

Neuron 2332 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1105234 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.4252. Min Act: -0.0000

Data Index: 989936 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3127. Min Act: -0.0000

Data Index: 85490 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2934. Min Act: -0.0000

Data Index: 671367 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2747. Min Act: -0.0000

Data Index: 753043 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2669. Min Act: -0.0000

Data Index: 810869 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2240. Min Act: -0.0000

Data Index: 335932 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2346. Min Act: -0.0000

Data Index: 730429 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2309. Min Act: -0.0000

Data Index: 786174 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2408. Min Act: -0.0000

Data Index: 359822 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2333. Min Act: -0.0000

Data Index: 1260496 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2476. Min Act: -0.0000

Data Index: 991541 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2241. Min Act: -0.0000

Data Index: 530915 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2238. Min Act: -0.0000

Data Index: 829259 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2205. Min Act: -0.0000

Data Index: 644205 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.1980. Min Act: -0.0000

Data Index: 649801 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2057. Min Act: -0.0000

Data Index: 728400 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2034. Min Act: -0.0000

Data Index: 4722 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2115. Min Act: -0.0000

Data Index: 768821 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2081. Min Act: -0.0000

Data Index: 997391 (C4 (Web Text))

Max Activating Token Index: 281