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

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

Neuron 1945 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1155565 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5879. Min Act: -0.0000

Data Index: 876320 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5246. Min Act: -0.0000

Data Index: 734908 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5085. Min Act: -0.0000

Data Index: 1200157 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5175. Min Act: -0.0000

Data Index: 956125 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5329. Min Act: -0.0001

Data Index: 1177572 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5051. Min Act: -0.0000

Data Index: 2241 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4838. Min Act: -0.0000

Data Index: 1258525 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5033. Min Act: -0.0000

Data Index: 332425 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5312. Min Act: -0.0000

Data Index: 241189 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5064. Min Act: -0.0000

Data Index: 32296 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4533. Min Act: -0.0000

Data Index: 945486 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5171. Min Act: -0.0000

Data Index: 383164 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4854. Min Act: -0.0000

Data Index: 641311 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4803. Min Act: -0.0000

Data Index: 1337293 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4743. Min Act: -0.0000

Data Index: 327469 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4521. Min Act: -0.0000

Data Index: 979113 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4585. Min Act: -0.0000

Data Index: 136717 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4398. Min Act: -0.0000

Data Index: 589616 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1240239 (C4 (Web Text))

Max Activating Token Index: 523