Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2679 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.3930. Min Act: -0.0000

Data Index: 1091545 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.3604. Min Act: -0.0000

Data Index: 653944 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.2330. Min Act: -0.0000

Data Index: 26435 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.3070. Min Act: -0.0000

Data Index: 1221450 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.2077. Min Act: -0.0000

Data Index: 726075 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.2058. Min Act: -0.0000

Data Index: 296389 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.2370. Min Act: -0.0000

Data Index: 713110 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.1517. Min Act: 0.0000

Data Index: 946061 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.1819. Min Act: -0.0000

Data Index: 1008221 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.1070. Min Act: -0.0000

Data Index: 1095316 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.2051. Min Act: -0.0000

Data Index: 433892 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.1303. Min Act: 0.0000

Data Index: 971725 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.1949. Min Act: -0.0000

Data Index: 239401 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.1500. Min Act: -0.0000

Data Index: 596922 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.1112. Min Act: -0.0000

Data Index: 555910 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.0822. Min Act: -0.0000

Data Index: 180020 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.0773. Min Act: -0.0000

Data Index: 72381 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.0633. Min Act: -0.0000

Data Index: 79421 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.0945. Min Act: -0.0000

Data Index: 247054 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 1.3930. Min Range: -1.3930

Max Act: 1.1054. Min Act: -0.0000

Data Index: 908161 (C4 (Web Text))

Max Activating Token Index: 145