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

Dataset: The Pile

Neuron 2356 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.9079. Min Act: -0.0000

Data Index: 407781 (The Pile)

Max Activating Token Index: 207

Text #1

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.9539. Min Act: -0.0000

Data Index: 1370590 (The Pile)

Max Activating Token Index: 551

Text #2

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1280157 (The Pile)

Max Activating Token Index: 354

Text #3

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.9212. Min Act: -0.0000

Data Index: 703361 (The Pile)

Max Activating Token Index: 309

Text #4

Max Range: 1.0258. Min Range: -1.0258

Max Act: 1.0258. Min Act: -0.0000

Data Index: 885288 (The Pile)

Max Activating Token Index: 466

Text #5

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7138. Min Act: -0.0000

Data Index: 1329649 (The Pile)

Max Activating Token Index: 79

Text #6

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1518065 (The Pile)

Max Activating Token Index: 166

Text #7

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.5525. Min Act: -0.0000

Data Index: 174995 (The Pile)

Max Activating Token Index: 610

Text #8

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.5631. Min Act: -0.0000

Data Index: 892959 (The Pile)

Max Activating Token Index: 57

Text #9

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.8074. Min Act: -0.0000

Data Index: 649227 (The Pile)

Max Activating Token Index: 872

Text #10

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6516. Min Act: -0.0000

Data Index: 1958457 (The Pile)

Max Activating Token Index: 1004

Text #11

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1952865 (The Pile)

Max Activating Token Index: 943

Text #12

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.5898. Min Act: -0.0000

Data Index: 708559 (The Pile)

Max Activating Token Index: 971

Text #13

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.5092. Min Act: -0.0000

Data Index: 399569 (The Pile)

Max Activating Token Index: 58

Text #14

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.4856. Min Act: -0.0000

Data Index: 183591 (The Pile)

Max Activating Token Index: 74

Text #15

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.5289. Min Act: -0.0000

Data Index: 395182 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.4659. Min Act: -0.0000

Data Index: 921826 (The Pile)

Max Activating Token Index: 899

Text #17

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.5505. Min Act: -0.0000

Data Index: 665628 (The Pile)

Max Activating Token Index: 231

Text #18

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6217. Min Act: -0.0000

Data Index: 66120 (The Pile)

Max Activating Token Index: 620

Text #19

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.5060. Min Act: -0.0000

Data Index: 869268 (The Pile)

Max Activating Token Index: 241