Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4284 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3052. Min Range: -1.3052

Max Act: 1.3052. Min Act: -0.0002

Data Index: 5491 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9861. Min Act: -0.0002

Data Index: 1220657 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 1.3052. Min Range: -1.3052

Max Act: 1.0371. Min Act: -0.0002

Data Index: 893626 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9656. Min Act: -0.0002

Data Index: 681467 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9548. Min Act: -0.0002

Data Index: 1276107 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9501. Min Act: -0.0002

Data Index: 1073592 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9515. Min Act: -0.0002

Data Index: 680070 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9731. Min Act: -0.0002

Data Index: 1263415 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9898. Min Act: -0.0002

Data Index: 1102884 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9312. Min Act: -0.0002

Data Index: 899356 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9553. Min Act: -0.0002

Data Index: 135497 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9530. Min Act: -0.0002

Data Index: 780465 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9589. Min Act: -0.0002

Data Index: 1163623 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.8993. Min Act: -0.0002

Data Index: 210353 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9021. Min Act: -0.0002

Data Index: 796104 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.8805. Min Act: -0.0002

Data Index: 181778 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.8721. Min Act: -0.0002

Data Index: 71417 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.8491. Min Act: -0.0002

Data Index: 262498 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.8784. Min Act: -0.0002

Data Index: 384063 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 1.3052. Min Range: -1.3052

Max Act: 0.9418. Min Act: -0.0002

Data Index: 446760 (C4 (Web Text))

Max Activating Token Index: 199