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

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

Neuron 3274 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.5470. Min Act: -0.0001

Data Index: 1193521 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.4438. Min Act: -0.0000

Data Index: 1354895 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.4764. Min Act: -0.0000

Data Index: 150742 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.5135. Min Act: -0.0000

Data Index: 796285 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.4541. Min Act: -0.0001

Data Index: 766847 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.4670. Min Act: -0.0000

Data Index: 441111 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.5148. Min Act: -0.0000

Data Index: 735172 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.4473. Min Act: -0.0000

Data Index: 873662 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.3818. Min Act: -0.0000

Data Index: 819806 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.4191. Min Act: -0.0000

Data Index: 967081 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.5098. Min Act: -0.0000

Data Index: 430799 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.4025. Min Act: -0.0000

Data Index: 1213806 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1051575 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.3641. Min Act: -0.0000

Data Index: 306411 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.4337. Min Act: -0.0000

Data Index: 30847 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.3790. Min Act: -0.0000

Data Index: 95840 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.3696. Min Act: -0.0000

Data Index: 400147 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1093864 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.3656. Min Act: -0.0000

Data Index: 1061528 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.5470. Min Range: -0.5470

Max Act: 0.3502. Min Act: -0.0001

Data Index: 812591 (C4 (Web Text))

Max Activating Token Index: 473