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

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

Neuron 5825 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8747. Min Range: -3.8747

Max Act: 3.8747. Min Act: -0.0000

Data Index: 378161 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 3.8747. Min Range: -3.8747

Max Act: 3.6330. Min Act: -0.0000

Data Index: 1241546 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 3.8747. Min Range: -3.8747

Max Act: 3.5075. Min Act: -0.0000

Data Index: 349196 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 3.8747. Min Range: -3.8747

Max Act: 3.6704. Min Act: -0.0000

Data Index: 646149 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 3.8747. Min Range: -3.8747

Max Act: 3.6014. Min Act: -0.0000

Data Index: 1348387 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 3.8747. Min Range: -3.8747

Max Act: 3.4218. Min Act: -0.0000

Data Index: 947914 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 3.8747. Min Range: -3.8747

Max Act: 3.4924. Min Act: -0.0000

Data Index: 257011 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 3.8747. Min Range: -3.8747

Max Act: 3.3909. Min Act: -0.0000

Data Index: 684767 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 3.8747. Min Range: -3.8747

Max Act: 3.1473. Min Act: -0.0000

Data Index: 163839 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 3.8747. Min Range: -3.8747

Max Act: 3.4570. Min Act: -0.0000

Data Index: 1114826 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 3.8747. Min Range: -3.8747

Max Act: 3.2589. Min Act: -0.0000

Data Index: 1150233 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 3.8747. Min Range: -3.8747

Max Act: 3.0878. Min Act: -0.0000

Data Index: 282069 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 3.8747. Min Range: -3.8747

Max Act: 3.0099. Min Act: -0.0000

Data Index: 72486 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 3.8747. Min Range: -3.8747

Max Act: 3.0060. Min Act: -0.0000

Data Index: 1017256 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 3.8747. Min Range: -3.8747

Max Act: 3.0456. Min Act: -0.0000

Data Index: 1215834 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 3.8747. Min Range: -3.8747

Max Act: 2.8996. Min Act: -0.0000

Data Index: 15673 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 3.8747. Min Range: -3.8747

Max Act: 2.9880. Min Act: -0.0000

Data Index: 263914 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 3.8747. Min Range: -3.8747

Max Act: 2.7254. Min Act: -0.0000

Data Index: 492425 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 3.8747. Min Range: -3.8747

Max Act: 2.5275. Min Act: -0.0000

Data Index: 1354781 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 3.8747. Min Range: -3.8747

Max Act: 2.4794. Min Act: 0.0000

Data Index: 563593 (C4 (Web Text))

Max Activating Token Index: 480