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

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

Neuron 1013 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.3078. Min Act: -0.0001

Data Index: 867296 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.3141. Min Act: -0.0001

Data Index: 743006 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2689. Min Act: -0.0001

Data Index: 738048 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2818. Min Act: -0.0001

Data Index: 1311245 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2525. Min Act: -0.0001

Data Index: 127302 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2754. Min Act: -0.0001

Data Index: 223123 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2508. Min Act: -0.0001

Data Index: 73541 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2491. Min Act: -0.0001

Data Index: 742142 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2317. Min Act: -0.0001

Data Index: 343459 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2445. Min Act: -0.0001

Data Index: 977639 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2335. Min Act: -0.0001

Data Index: 861159 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2317. Min Act: -0.0001

Data Index: 449816 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2430. Min Act: -0.0001

Data Index: 320308 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2168. Min Act: -0.0001

Data Index: 626431 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2272. Min Act: -0.0001

Data Index: 782129 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.1982. Min Act: -0.0001

Data Index: 887707 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2044. Min Act: -0.0001

Data Index: 1126575 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2174. Min Act: -0.0001

Data Index: 834173 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2161. Min Act: -0.0001

Data Index: 416316 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.3141. Min Range: -0.3141

Max Act: 0.2064. Min Act: -0.0001

Data Index: 1321704 (C4 (Web Text))

Max Activating Token Index: 254