Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1611 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.8060. Min Act: -0.0000

Data Index: 750127 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.4849. Min Act: -0.0001

Data Index: 1121632 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.4625. Min Act: -0.0001

Data Index: 222250 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.4299. Min Act: -0.0001

Data Index: 259552 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.4406. Min Act: -0.0001

Data Index: 797346 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.1668. Min Act: -0.0000

Data Index: 757292 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.1332. Min Act: -0.0000

Data Index: 341054 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.0800. Min Act: -0.0000

Data Index: 825455 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.1162. Min Act: -0.0000

Data Index: 47647 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.1289. Min Act: 0.0000

Data Index: 1039603 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.0490. Min Act: -0.0000

Data Index: 579644 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.0931. Min Act: -0.0000

Data Index: 142766 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.1196. Min Act: -0.0000

Data Index: 685326 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.0198. Min Act: -0.0000

Data Index: 349006 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.0087. Min Act: -0.0000

Data Index: 196570 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 1.8060. Min Range: -1.8060

Max Act: 0.9683. Min Act: -0.0000

Data Index: 578925 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 1.8060. Min Range: -1.8060

Max Act: 0.9666. Min Act: 0.0000

Data Index: 1104039 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 1.8060. Min Range: -1.8060

Max Act: 0.9654. Min Act: -0.0000

Data Index: 437752 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 1.8060. Min Range: -1.8060

Max Act: 0.9662. Min Act: -0.0000

Data Index: 657151 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.0204. Min Act: -0.0000

Data Index: 102702 (C4 (Web Text))

Max Activating Token Index: 777