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

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

Neuron 2454 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.5083. Min Act: -0.0000

Data Index: 400690 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.3477. Min Act: -0.0000

Data Index: 610073 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.3226. Min Act: -0.0000

Data Index: 103201 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.3067. Min Act: -0.0000

Data Index: 999516 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.2877. Min Act: -0.0000

Data Index: 875450 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.2267. Min Act: -0.0000

Data Index: 422249 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.3184. Min Act: -0.0000

Data Index: 509272 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.2969. Min Act: -0.0000

Data Index: 228336 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.1318. Min Act: -0.0000

Data Index: 1284884 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.3433. Min Act: -0.0000

Data Index: 269693 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.2172. Min Act: -0.0000

Data Index: 79493 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.2107. Min Act: -0.0000

Data Index: 814857 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.1340. Min Act: -0.0000

Data Index: 1217746 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.0784. Min Act: -0.0000

Data Index: 573802 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.1536. Min Act: -0.0000

Data Index: 515053 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.1765. Min Act: -0.0000

Data Index: 998360 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.1466. Min Act: -0.0000

Data Index: 1095516 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.1931. Min Act: -0.0000

Data Index: 933738 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.1400. Min Act: -0.0000

Data Index: 57562 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 2.5083. Min Range: -2.5083

Max Act: 2.0254. Min Act: -0.0000

Data Index: 969613 (C4 (Web Text))

Max Activating Token Index: 463