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

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

Neuron 4963 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.5035. Min Act: -0.0000

Data Index: 719929 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.6288. Min Act: -0.0000

Data Index: 1068088 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.6089. Min Act: -0.0000

Data Index: 266980 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.5774. Min Act: -0.0000

Data Index: 389297 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.5145. Min Act: -0.0000

Data Index: 749974 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.4930. Min Act: -0.0000

Data Index: 418425 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.4427. Min Act: -0.0000

Data Index: 1334828 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.4556. Min Act: -0.0000

Data Index: 1272934 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.3989. Min Act: -0.0000

Data Index: 831143 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.5431. Min Act: -0.0000

Data Index: 871590 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.4046. Min Act: -0.0000

Data Index: 331391 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.1827. Min Act: -0.0000

Data Index: 746915 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.3382. Min Act: -0.0000

Data Index: 1046504 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.0499. Min Act: -0.0000

Data Index: 1023073 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.1742. Min Act: -0.0000

Data Index: 248166 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.1488. Min Act: -0.0000

Data Index: 1306977 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.3095. Min Act: -0.0000

Data Index: 1296450 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.4700. Min Act: -0.0000

Data Index: 821883 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.1523. Min Act: -0.0000

Data Index: 330960 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 3.6288. Min Range: -3.6288

Max Act: 3.1444. Min Act: -0.0000

Data Index: 288299 (C4 (Web Text))

Max Activating Token Index: 552