Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1311 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1793. Min Range: -1.1793

Max Act: 1.1793. Min Act: -0.0001

Data Index: 505046 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 1.1793. Min Range: -1.1793

Max Act: 1.0724. Min Act: -0.0001

Data Index: 664093 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 1.1793. Min Range: -1.1793

Max Act: 1.0384. Min Act: -0.0001

Data Index: 164850 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 1.1793. Min Range: -1.1793

Max Act: 1.0362. Min Act: -0.0001

Data Index: 657290 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.9410. Min Act: -0.0001

Data Index: 557306 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.8377. Min Act: -0.0001

Data Index: 1345291 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.8632. Min Act: -0.0001

Data Index: 805535 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.7587. Min Act: -0.0001

Data Index: 696376 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.7475. Min Act: -0.0001

Data Index: 1024736 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.7656. Min Act: -0.0001

Data Index: 209028 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.8094. Min Act: -0.0001

Data Index: 619052 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.7274. Min Act: -0.0001

Data Index: 469810 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.7457. Min Act: -0.0001

Data Index: 1097471 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.7725. Min Act: -0.0001

Data Index: 76942 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.7507. Min Act: -0.0001

Data Index: 484180 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.7458. Min Act: -0.0001

Data Index: 41810 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.6955. Min Act: -0.0001

Data Index: 232311 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.7137. Min Act: -0.0001

Data Index: 509819 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.7267. Min Act: -0.0001

Data Index: 865014 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 1.1793. Min Range: -1.1793

Max Act: 0.7441. Min Act: -0.0001

Data Index: 669524 (C4 (Web Text))

Max Activating Token Index: 159