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

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

Neuron 4697 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3610. Min Range: -1.3610

Max Act: 1.3538. Min Act: -0.0000

Data Index: 244303 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 1.3610. Min Range: -1.3610

Max Act: 1.3610. Min Act: -0.0000

Data Index: 278159 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 1.3610. Min Range: -1.3610

Max Act: 1.2757. Min Act: -0.0000

Data Index: 1135535 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 1.3610. Min Range: -1.3610

Max Act: 1.2237. Min Act: -0.0000

Data Index: 1098788 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 1.3610. Min Range: -1.3610

Max Act: 1.1547. Min Act: -0.0000

Data Index: 1195907 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 1.3610. Min Range: -1.3610

Max Act: 1.1521. Min Act: -0.0000

Data Index: 864399 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 1.3610. Min Range: -1.3610

Max Act: 1.1386. Min Act: -0.0000

Data Index: 648737 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 1.3610. Min Range: -1.3610

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1344920 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 1.3610. Min Range: -1.3610

Max Act: 1.0964. Min Act: -0.0000

Data Index: 265371 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 1.3610. Min Range: -1.3610

Max Act: 1.0981. Min Act: -0.0000

Data Index: 416191 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 1.3610. Min Range: -1.3610

Max Act: 1.0956. Min Act: -0.0000

Data Index: 1071265 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 1.3610. Min Range: -1.3610

Max Act: 1.0528. Min Act: -0.0000

Data Index: 419347 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 1.3610. Min Range: -1.3610

Max Act: 1.0338. Min Act: -0.0000

Data Index: 431567 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 1.3610. Min Range: -1.3610

Max Act: 1.0738. Min Act: -0.0000

Data Index: 867217 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 1.3610. Min Range: -1.3610

Max Act: 0.9981. Min Act: -0.0000

Data Index: 1122317 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 1.3610. Min Range: -1.3610

Max Act: 0.9333. Min Act: -0.0000

Data Index: 102276 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 1.3610. Min Range: -1.3610

Max Act: 0.9875. Min Act: -0.0000

Data Index: 315107 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 1.3610. Min Range: -1.3610

Max Act: 0.9335. Min Act: -0.0000

Data Index: 783936 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 1.3610. Min Range: -1.3610

Max Act: 0.9845. Min Act: -0.0000

Data Index: 722373 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 1.3610. Min Range: -1.3610

Max Act: 0.9865. Min Act: -0.0000

Data Index: 434325 (C4 (Web Text))

Max Activating Token Index: 574