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

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

Neuron 1816 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8158. Min Act: -0.0000

Data Index: 276907 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.8747. Min Act: -0.0000

Data Index: 1040248 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.7081. Min Act: -0.0000

Data Index: 297834 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.4309. Min Act: -0.0000

Data Index: 388376 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.6561. Min Act: -0.0000

Data Index: 1221977 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.5583. Min Act: -0.0000

Data Index: 619127 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.4401. Min Act: -0.0000

Data Index: 785937 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.5124. Min Act: -0.0000

Data Index: 852931 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.5350. Min Act: -0.0000

Data Index: 152298 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.5037. Min Act: -0.0000

Data Index: 184085 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.3959. Min Act: -0.0000

Data Index: 477090 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.4905. Min Act: -0.0000

Data Index: 1104326 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.4462. Min Act: -0.0000

Data Index: 1051677 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.4882. Min Act: -0.0000

Data Index: 883963 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.4020. Min Act: -0.0000

Data Index: 489081 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.4112. Min Act: -0.0000

Data Index: 275158 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.3656. Min Act: -0.0000

Data Index: 738958 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.3941. Min Act: -0.0000

Data Index: 429507 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.3196. Min Act: -0.0000

Data Index: 880068 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 1.8747. Min Range: -1.8747

Max Act: 1.3133. Min Act: -0.0000

Data Index: 641038 (C4 (Web Text))

Max Activating Token Index: 125