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

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

Neuron 3057 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: 1.6145. Min Range: -1.6145

Max Act: 1.6145. Min Act: -0.0002

Data Index: 772236 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.5754. Min Act: -0.0002

Data Index: 374045 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.3870. Min Act: -0.0002

Data Index: 1006664 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.4468. Min Act: -0.0002

Data Index: 578056 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.3512. Min Act: -0.0002

Data Index: 727572 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.3767. Min Act: -0.0002

Data Index: 103045 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.3945. Min Act: -0.0002

Data Index: 715833 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.3412. Min Act: -0.0002

Data Index: 728167 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.3039. Min Act: -0.0002

Data Index: 543692 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.2773. Min Act: -0.0002

Data Index: 1303893 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.3268. Min Act: -0.0002

Data Index: 847295 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.2901. Min Act: -0.0002

Data Index: 185312 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.3272. Min Act: -0.0002

Data Index: 243015 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.2688. Min Act: -0.0002

Data Index: 280836 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.2579. Min Act: -0.0002

Data Index: 644077 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.2873. Min Act: -0.0002

Data Index: 1101064 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.2608. Min Act: -0.0002

Data Index: 977986 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.2354. Min Act: -0.0002

Data Index: 610580 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.2326. Min Act: -0.0002

Data Index: 1281562 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 1.6145. Min Range: -1.6145

Max Act: 1.2091. Min Act: -0.0002

Data Index: 902302 (C4 (Web Text))

Max Activating Token Index: 791