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

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

Neuron 730 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4433. Min Range: -2.4433

Max Act: 2.4433. Min Act: -0.0000

Data Index: 210618 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 2.4433. Min Range: -2.4433

Max Act: 2.0293. Min Act: -0.0000

Data Index: 679645 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 2.4433. Min Range: -2.4433

Max Act: 2.0764. Min Act: -0.0000

Data Index: 88077 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 2.4433. Min Range: -2.4433

Max Act: 1.8710. Min Act: -0.0000

Data Index: 882126 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 2.4433. Min Range: -2.4433

Max Act: 1.9249. Min Act: -0.0000

Data Index: 1032955 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 2.4433. Min Range: -2.4433

Max Act: 1.8582. Min Act: -0.0000

Data Index: 1316957 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 2.4433. Min Range: -2.4433

Max Act: 1.9484. Min Act: -0.0000

Data Index: 789106 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 2.4433. Min Range: -2.4433

Max Act: 1.8252. Min Act: -0.0000

Data Index: 73924 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 2.4433. Min Range: -2.4433

Max Act: 1.7449. Min Act: -0.0000

Data Index: 200868 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 2.4433. Min Range: -2.4433

Max Act: 1.8875. Min Act: -0.0000

Data Index: 369285 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 2.4433. Min Range: -2.4433

Max Act: 1.7831. Min Act: -0.0000

Data Index: 808885 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 2.4433. Min Range: -2.4433

Max Act: 1.4979. Min Act: -0.0000

Data Index: 308724 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 2.4433. Min Range: -2.4433

Max Act: 1.7707. Min Act: -0.0000

Data Index: 1151136 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 2.4433. Min Range: -2.4433

Max Act: 1.8349. Min Act: -0.0000

Data Index: 101368 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 2.4433. Min Range: -2.4433

Max Act: 1.6347. Min Act: -0.0000

Data Index: 213515 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 2.4433. Min Range: -2.4433

Max Act: 1.7052. Min Act: -0.0000

Data Index: 791549 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 2.4433. Min Range: -2.4433

Max Act: 1.6664. Min Act: -0.0000

Data Index: 1233551 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 2.4433. Min Range: -2.4433

Max Act: 1.5451. Min Act: -0.0000

Data Index: 1057634 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 2.4433. Min Range: -2.4433

Max Act: 1.6186. Min Act: -0.0000

Data Index: 347989 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 2.4433. Min Range: -2.4433

Max Act: 1.6335. Min Act: -0.0000

Data Index: 1169108 (C4 (Web Text))

Max Activating Token Index: 35