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

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

Neuron 4866 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: 0.7233. Min Range: -0.7233

Max Act: 0.7233. Min Act: -0.0000

Data Index: 1007376 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.7170. Min Act: -0.0000

Data Index: 788728 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1052566 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.6616. Min Act: -0.0000

Data Index: 53426 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1173704 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.6137. Min Act: 0.0001

Data Index: 950696 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5741. Min Act: -0.0000

Data Index: 562606 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.6199. Min Act: -0.0000

Data Index: 941945 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.6106. Min Act: 0.0000

Data Index: 1040308 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.6012. Min Act: -0.0000

Data Index: 35098 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5886. Min Act: -0.0000

Data Index: 632579 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5858. Min Act: 0.0000

Data Index: 561466 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5591. Min Act: -0.0000

Data Index: 91816 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5554. Min Act: 0.0000

Data Index: 245904 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5163. Min Act: 0.0001

Data Index: 301511 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5490. Min Act: -0.0000

Data Index: 347214 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5187. Min Act: 0.0000

Data Index: 1315215 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5455. Min Act: -0.0000

Data Index: 249788 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5386. Min Act: -0.0000

Data Index: 637637 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 0.7233. Min Range: -0.7233

Max Act: 0.5430. Min Act: 0.0000

Data Index: 826014 (C4 (Web Text))

Max Activating Token Index: 405