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

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

Neuron 1817 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1107. Min Range: -4.1107

Max Act: 4.1107. Min Act: -0.0000

Data Index: 674181 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 4.1107. Min Range: -4.1107

Max Act: 3.8065. Min Act: -0.0000

Data Index: 199721 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 4.1107. Min Range: -4.1107

Max Act: 3.9735. Min Act: -0.0000

Data Index: 773826 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 4.1107. Min Range: -4.1107

Max Act: 3.6495. Min Act: -0.0000

Data Index: 670874 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 4.1107. Min Range: -4.1107

Max Act: 3.7144. Min Act: -0.0000

Data Index: 106965 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 4.1107. Min Range: -4.1107

Max Act: 3.8338. Min Act: -0.0000

Data Index: 1261572 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 4.1107. Min Range: -4.1107

Max Act: 3.6207. Min Act: -0.0000

Data Index: 719132 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 4.1107. Min Range: -4.1107

Max Act: 3.4963. Min Act: -0.0000

Data Index: 375312 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 4.1107. Min Range: -4.1107

Max Act: 3.4895. Min Act: -0.0000

Data Index: 712257 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 4.1107. Min Range: -4.1107

Max Act: 3.4660. Min Act: -0.0000

Data Index: 263965 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 4.1107. Min Range: -4.1107

Max Act: 3.6284. Min Act: -0.0000

Data Index: 980492 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 4.1107. Min Range: -4.1107

Max Act: 3.2655. Min Act: -0.0000

Data Index: 574238 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 4.1107. Min Range: -4.1107

Max Act: 3.3087. Min Act: -0.0000

Data Index: 1276798 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 4.1107. Min Range: -4.1107

Max Act: 3.2815. Min Act: -0.0000

Data Index: 253150 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 4.1107. Min Range: -4.1107

Max Act: 3.2436. Min Act: -0.0000

Data Index: 1262357 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 4.1107. Min Range: -4.1107

Max Act: 3.2298. Min Act: -0.0000

Data Index: 609410 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 4.1107. Min Range: -4.1107

Max Act: 3.4978. Min Act: -0.0000

Data Index: 1113376 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 4.1107. Min Range: -4.1107

Max Act: 3.1476. Min Act: -0.0000

Data Index: 407523 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 4.1107. Min Range: -4.1107

Max Act: 2.8614. Min Act: -0.0000

Data Index: 108093 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 4.1107. Min Range: -4.1107

Max Act: 2.9775. Min Act: -0.0000

Data Index: 113583 (C4 (Web Text))

Max Activating Token Index: 9