Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2513 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7815. Min Act: -0.0001

Data Index: 1260068 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.7346. Min Act: -0.0001

Data Index: 858250 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.6929. Min Act: -0.0001

Data Index: 91612 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5618. Min Act: -0.0001

Data Index: 547728 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5287. Min Act: -0.0001

Data Index: 1134353 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5415. Min Act: -0.0001

Data Index: 1078325 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5220. Min Act: -0.0001

Data Index: 140839 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5527. Min Act: -0.0001

Data Index: 405730 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5342. Min Act: -0.0001

Data Index: 418145 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.4926. Min Act: -0.0001

Data Index: 86634 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5154. Min Act: -0.0001

Data Index: 790123 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5323. Min Act: -0.0001

Data Index: 539282 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5131. Min Act: -0.0001

Data Index: 1022335 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.4953. Min Act: -0.0001

Data Index: 1044216 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5093. Min Act: -0.0001

Data Index: 153052 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5087. Min Act: -0.0001

Data Index: 159560 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.5082. Min Act: -0.0001

Data Index: 1095000 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.4693. Min Act: -0.0001

Data Index: 619992 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.4653. Min Act: -0.0001

Data Index: 872800 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 0.7815. Min Range: -0.7815

Max Act: 0.4786. Min Act: -0.0001

Data Index: 457361 (C4 (Web Text))

Max Activating Token Index: 334