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

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

Neuron 1792 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.4097. Min Act: -0.0000

Data Index: 662351 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.3577. Min Act: -0.0000

Data Index: 934011 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2645. Min Act: -0.0000

Data Index: 412571 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2573. Min Act: -0.0000

Data Index: 365089 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2356. Min Act: -0.0000

Data Index: 167290 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1122769 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1124711 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2403. Min Act: -0.0000

Data Index: 1533115 (Python Code)

Max Activating Token Index: 446

Text #8

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1201909 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2256. Min Act: -0.0000

Data Index: 754870 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2097. Min Act: -0.0000

Data Index: 1107212 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2125. Min Act: -0.0000

Data Index: 983043 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2098. Min Act: -0.0000

Data Index: 700098 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1226922 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.1993. Min Act: -0.0000

Data Index: 159591 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2109. Min Act: -0.0000

Data Index: 825229 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.1900. Min Act: -0.0000

Data Index: 678658 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.1958. Min Act: -0.0000

Data Index: 620617 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.2008. Min Act: -0.0000

Data Index: 681567 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.4097. Min Range: -0.4097

Max Act: 0.1930. Min Act: -0.0000

Data Index: 796127 (C4 (Web Text))

Max Activating Token Index: 96