Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1706 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.2291. Min Range: -1.2291

Max Act: 1.2291. Min Act: -0.0001

Data Index: 1174558 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 1.2291. Min Range: -1.2291

Max Act: 1.1465. Min Act: -0.0001

Data Index: 1075669 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 1.2291. Min Range: -1.2291

Max Act: 1.1292. Min Act: -0.0001

Data Index: 541149 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 1.2291. Min Range: -1.2291

Max Act: 1.1425. Min Act: -0.0001

Data Index: 967091 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 1.2291. Min Range: -1.2291

Max Act: 1.0843. Min Act: -0.0001

Data Index: 738574 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 1.2291. Min Range: -1.2291

Max Act: 1.0433. Min Act: -0.0001

Data Index: 520574 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 1.2291. Min Range: -1.2291

Max Act: 1.0499. Min Act: -0.0001

Data Index: 388445 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 1.2291. Min Range: -1.2291

Max Act: 1.0848. Min Act: -0.0001

Data Index: 695313 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 1.2291. Min Range: -1.2291

Max Act: 1.0195. Min Act: -0.0001

Data Index: 31960 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 1.2291. Min Range: -1.2291

Max Act: 1.0161. Min Act: -0.0001

Data Index: 88410 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 1.2291. Min Range: -1.2291

Max Act: 1.0101. Min Act: -0.0001

Data Index: 742252 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 1.2291. Min Range: -1.2291

Max Act: 1.1013. Min Act: -0.0001

Data Index: 258790 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 1.2291. Min Range: -1.2291

Max Act: 0.9691. Min Act: -0.0001

Data Index: 71765 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 1.2291. Min Range: -1.2291

Max Act: 1.0239. Min Act: -0.0001

Data Index: 14228 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 1.2291. Min Range: -1.2291

Max Act: 0.9913. Min Act: -0.0001

Data Index: 104441 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 1.2291. Min Range: -1.2291

Max Act: 0.9797. Min Act: -0.0001

Data Index: 729130 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 1.2291. Min Range: -1.2291

Max Act: 1.0119. Min Act: -0.0001

Data Index: 871403 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 1.2291. Min Range: -1.2291

Max Act: 1.0010. Min Act: -0.0001

Data Index: 218935 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 1.2291. Min Range: -1.2291

Max Act: 0.9705. Min Act: -0.0001

Data Index: 813269 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 1.2291. Min Range: -1.2291

Max Act: 0.9963. Min Act: -0.0001

Data Index: 287451 (C4 (Web Text))

Max Activating Token Index: 963