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

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

Neuron 1938 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0497. Min Range: -3.0497

Max Act: 3.0497. Min Act: -0.0000

Data Index: 795298 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 3.0497. Min Range: -3.0497

Max Act: 3.0129. Min Act: -0.0000

Data Index: 292714 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 3.0497. Min Range: -3.0497

Max Act: 2.9830. Min Act: -0.0000

Data Index: 603200 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 3.0497. Min Range: -3.0497

Max Act: 2.7894. Min Act: -0.0000

Data Index: 275156 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 3.0497. Min Range: -3.0497

Max Act: 2.7312. Min Act: -0.0000

Data Index: 1496811 (Python Code)

Max Activating Token Index: 946

Text #5

Max Range: 3.0497. Min Range: -3.0497

Max Act: 2.8503. Min Act: -0.0000

Data Index: 57100 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 3.0497. Min Range: -3.0497

Max Act: 2.8533. Min Act: 0.0000

Data Index: 64607 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 3.0497. Min Range: -3.0497

Max Act: 2.5789. Min Act: -0.0000

Data Index: 1534489 (Python Code)

Max Activating Token Index: 296

Text #8

Max Range: 3.0497. Min Range: -3.0497

Max Act: 2.7672. Min Act: -0.0000

Data Index: 322295 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 3.0497. Min Range: -3.0497

Max Act: 2.6255. Min Act: -0.0000

Data Index: 1305551 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 3.0497. Min Range: -3.0497

Max Act: 2.6270. Min Act: -0.0000

Data Index: 1370070 (Python Code)

Max Activating Token Index: 563

Text #11

Max Range: 3.0497. Min Range: -3.0497

Max Act: 2.4735. Min Act: -0.0000

Data Index: 514443 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 3.0497. Min Range: -3.0497

Max Act: 2.5777. Min Act: -0.0000

Data Index: 8816 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 3.0497. Min Range: -3.0497

Max Act: 2.4335. Min Act: -0.0000

Data Index: 536897 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 3.0497. Min Range: -3.0497

Max Act: 2.5406. Min Act: -0.0000

Data Index: 523216 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 3.0497. Min Range: -3.0497

Max Act: 2.5324. Min Act: -0.0000

Data Index: 522327 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 3.0497. Min Range: -3.0497

Max Act: 2.6469. Min Act: -0.0000

Data Index: 268604 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 3.0497. Min Range: -3.0497

Max Act: 2.6809. Min Act: -0.0000

Data Index: 815487 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 3.0497. Min Range: -3.0497

Max Act: 2.4375. Min Act: -0.0000

Data Index: 1150572 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 3.0497. Min Range: -3.0497

Max Act: 2.4643. Min Act: -0.0000

Data Index: 1143474 (C4 (Web Text))

Max Activating Token Index: 294