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

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

Neuron 5071 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: 2.3111. Min Range: -2.3111

Max Act: 2.3111. Min Act: -0.0000

Data Index: 748109 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 2.3111. Min Range: -2.3111

Max Act: 2.1081. Min Act: -0.0000

Data Index: 1055058 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 2.3111. Min Range: -2.3111

Max Act: 1.8836. Min Act: -0.0000

Data Index: 667805 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 2.3111. Min Range: -2.3111

Max Act: 1.8791. Min Act: -0.0000

Data Index: 67886 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 2.3111. Min Range: -2.3111

Max Act: 1.8152. Min Act: -0.0000

Data Index: 619112 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 2.3111. Min Range: -2.3111

Max Act: 1.6903. Min Act: -0.0000

Data Index: 955830 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 2.3111. Min Range: -2.3111

Max Act: 1.7686. Min Act: -0.0000

Data Index: 452944 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 2.3111. Min Range: -2.3111

Max Act: 1.7042. Min Act: -0.0000

Data Index: 851178 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 2.3111. Min Range: -2.3111

Max Act: 1.6938. Min Act: -0.0000

Data Index: 1186245 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 2.3111. Min Range: -2.3111

Max Act: 1.4963. Min Act: -0.0000

Data Index: 802093 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 2.3111. Min Range: -2.3111

Max Act: 1.6606. Min Act: -0.0000

Data Index: 977 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 2.3111. Min Range: -2.3111

Max Act: 1.5730. Min Act: -0.0000

Data Index: 167928 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 2.3111. Min Range: -2.3111

Max Act: 1.5513. Min Act: -0.0000

Data Index: 439527 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 2.3111. Min Range: -2.3111

Max Act: 1.6397. Min Act: -0.0000

Data Index: 945006 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 2.3111. Min Range: -2.3111

Max Act: 1.6113. Min Act: -0.0000

Data Index: 591476 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 2.3111. Min Range: -2.3111

Max Act: 1.6130. Min Act: -0.0000

Data Index: 1164574 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 2.3111. Min Range: -2.3111

Max Act: 1.5910. Min Act: -0.0000

Data Index: 1230239 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 2.3111. Min Range: -2.3111

Max Act: 1.3273. Min Act: -0.0000

Data Index: 580935 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 2.3111. Min Range: -2.3111

Max Act: 1.3947. Min Act: -0.0000

Data Index: 979392 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 2.3111. Min Range: -2.3111

Max Act: 1.6314. Min Act: -0.0000

Data Index: 91389 (C4 (Web Text))

Max Activating Token Index: 292