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

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

Neuron 1183 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9648. Min Range: -4.9648

Max Act: 4.6413. Min Act: -0.0001

Data Index: 1008250 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 4.9648. Min Range: -4.9648

Max Act: 4.7630. Min Act: -0.0001

Data Index: 1290483 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 4.9648. Min Range: -4.9648

Max Act: 4.7214. Min Act: -0.0001

Data Index: 157550 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 4.9648. Min Range: -4.9648

Max Act: 4.6516. Min Act: -0.0001

Data Index: 154241 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 4.9648. Min Range: -4.9648

Max Act: 4.6211. Min Act: -0.0001

Data Index: 1070711 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 4.9648. Min Range: -4.9648

Max Act: 4.6075. Min Act: -0.0000

Data Index: 297780 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 4.9648. Min Range: -4.9648

Max Act: 4.9648. Min Act: -0.0001

Data Index: 247435 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 4.9648. Min Range: -4.9648

Max Act: 4.4967. Min Act: -0.0000

Data Index: 1129379 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 4.9648. Min Range: -4.9648

Max Act: 4.4802. Min Act: -0.0001

Data Index: 1173010 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 4.9648. Min Range: -4.9648

Max Act: 3.6816. Min Act: -0.0000

Data Index: 626557 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 4.9648. Min Range: -4.9648

Max Act: 4.4483. Min Act: -0.0001

Data Index: 767935 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 4.9648. Min Range: -4.9648

Max Act: 3.7290. Min Act: -0.0000

Data Index: 126474 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 4.9648. Min Range: -4.9648

Max Act: 4.0340. Min Act: -0.0000

Data Index: 273803 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 4.9648. Min Range: -4.9648

Max Act: 4.1410. Min Act: -0.0001

Data Index: 767773 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 4.9648. Min Range: -4.9648

Max Act: 3.3676. Min Act: -0.0001

Data Index: 187880 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 4.9648. Min Range: -4.9648

Max Act: 4.0980. Min Act: -0.0000

Data Index: 87876 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 4.9648. Min Range: -4.9648

Max Act: 4.2586. Min Act: -0.0001

Data Index: 887573 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 4.9648. Min Range: -4.9648

Max Act: 4.0567. Min Act: -0.0000

Data Index: 724352 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 4.9648. Min Range: -4.9648

Max Act: 4.3144. Min Act: -0.0001

Data Index: 368362 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 4.9648. Min Range: -4.9648

Max Act: 4.3190. Min Act: -0.0001

Data Index: 809492 (C4 (Web Text))

Max Activating Token Index: 356