Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1599 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7503. Min Act: -0.0000

Data Index: 311148 (The Pile)

Max Activating Token Index: 901

Text #1

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7857. Min Act: -0.0000

Data Index: 1187455 (The Pile)

Max Activating Token Index: 994

Text #2

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7402. Min Act: -0.0000

Data Index: 1514823 (The Pile)

Max Activating Token Index: 109

Text #3

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.8330. Min Act: -0.0000

Data Index: 1922229 (The Pile)

Max Activating Token Index: 972

Text #4

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6917. Min Act: -0.0000

Data Index: 234736 (The Pile)

Max Activating Token Index: 812

Text #5

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7355. Min Act: -0.0000

Data Index: 589396 (The Pile)

Max Activating Token Index: 714

Text #6

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7313. Min Act: -0.0000

Data Index: 245200 (The Pile)

Max Activating Token Index: 804

Text #7

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7051. Min Act: -0.0000

Data Index: 992486 (The Pile)

Max Activating Token Index: 796

Text #8

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6919. Min Act: -0.0000

Data Index: 1575370 (The Pile)

Max Activating Token Index: 304

Text #9

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6974. Min Act: -0.0000

Data Index: 236511 (The Pile)

Max Activating Token Index: 92

Text #10

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6774. Min Act: -0.0000

Data Index: 1537145 (The Pile)

Max Activating Token Index: 794

Text #11

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.7689. Min Act: -0.0000

Data Index: 453345 (The Pile)

Max Activating Token Index: 931

Text #12

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6773. Min Act: -0.0000

Data Index: 531463 (The Pile)

Max Activating Token Index: 711

Text #13

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6133. Min Act: -0.0000

Data Index: 1695811 (The Pile)

Max Activating Token Index: 933

Text #14

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6160. Min Act: -0.0000

Data Index: 311931 (The Pile)

Max Activating Token Index: 797

Text #15

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1949177 (The Pile)

Max Activating Token Index: 680

Text #16

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6712. Min Act: -0.0000

Data Index: 1210685 (The Pile)

Max Activating Token Index: 363

Text #17

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.5939. Min Act: -0.0000

Data Index: 342713 (The Pile)

Max Activating Token Index: 492

Text #18

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6617. Min Act: -0.0000

Data Index: 469706 (The Pile)

Max Activating Token Index: 190

Text #19

Max Range: 0.8330. Min Range: -0.8330

Max Act: 0.6187. Min Act: -0.0000

Data Index: 686676 (The Pile)

Max Activating Token Index: 222