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

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

Neuron 1516 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: 0.2400. Min Range: -0.2400

Max Act: 0.2400. Min Act: -0.0000

Data Index: 738385 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2222. Min Act: -0.0000

Data Index: 170320 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2144. Min Act: -0.0000

Data Index: 472089 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2066. Min Act: -0.0000

Data Index: 968650 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2079. Min Act: -0.0000

Data Index: 120191 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2136. Min Act: -0.0000

Data Index: 878401 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1932. Min Act: -0.0000

Data Index: 461046 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2075. Min Act: -0.0000

Data Index: 151428 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1956. Min Act: -0.0000

Data Index: 245899 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1920. Min Act: -0.0000

Data Index: 24677 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1109740 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1920. Min Act: -0.0000

Data Index: 522474 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1912. Min Act: -0.0000

Data Index: 906646 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1962. Min Act: -0.0000

Data Index: 851264 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1827. Min Act: -0.0000

Data Index: 781302 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1104488 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1998. Min Act: -0.0000

Data Index: 680848 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1146153 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1948. Min Act: -0.0000

Data Index: 119979 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.1760. Min Act: -0.0000

Data Index: 626870 (C4 (Web Text))

Max Activating Token Index: 78