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

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

Neuron 2745 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.5468. Min Act: -0.0002

Data Index: 1146527 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.5029. Min Act: -0.0002

Data Index: 294241 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.4551. Min Act: -0.0002

Data Index: 57449 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3938. Min Act: -0.0002

Data Index: 60003 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3904. Min Act: -0.0002

Data Index: 1338309 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3886. Min Act: -0.0002

Data Index: 563099 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3563. Min Act: -0.0002

Data Index: 1284451 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3800. Min Act: -0.0002

Data Index: 149647 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3474. Min Act: -0.0002

Data Index: 890301 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3661. Min Act: -0.0002

Data Index: 1329145 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3162. Min Act: -0.0002

Data Index: 809138 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3334. Min Act: -0.0002

Data Index: 407899 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3907. Min Act: -0.0002

Data Index: 336983 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3346. Min Act: -0.0002

Data Index: 538771 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3380. Min Act: -0.0002

Data Index: 542678 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3558. Min Act: -0.0002

Data Index: 943422 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3297. Min Act: -0.0002

Data Index: 1079170 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3352. Min Act: -0.0002

Data Index: 792954 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3381. Min Act: -0.0002

Data Index: 1007885 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 1.5468. Min Range: -1.5468

Max Act: 1.3247. Min Act: -0.0002

Data Index: 155284 (C4 (Web Text))

Max Activating Token Index: 656