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

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

Neuron 5064 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0928. Min Range: -4.0928

Max Act: 4.0928. Min Act: -0.0000

Data Index: 709074 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 4.0928. Min Range: -4.0928

Max Act: 4.0509. Min Act: -0.0000

Data Index: 697274 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 4.0928. Min Range: -4.0928

Max Act: 3.9171. Min Act: -0.0000

Data Index: 1116620 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 4.0928. Min Range: -4.0928

Max Act: 3.9188. Min Act: -0.0000

Data Index: 1107105 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 4.0928. Min Range: -4.0928

Max Act: 3.9040. Min Act: -0.0000

Data Index: 46612 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 4.0928. Min Range: -4.0928

Max Act: 3.6733. Min Act: -0.0000

Data Index: 804191 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 4.0928. Min Range: -4.0928

Max Act: 3.7398. Min Act: -0.0000

Data Index: 1291973 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 4.0928. Min Range: -4.0928

Max Act: 3.6937. Min Act: -0.0000

Data Index: 1079712 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 4.0928. Min Range: -4.0928

Max Act: 3.6731. Min Act: -0.0000

Data Index: 511112 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 4.0928. Min Range: -4.0928

Max Act: 3.6599. Min Act: -0.0000

Data Index: 539035 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 4.0928. Min Range: -4.0928

Max Act: 3.6025. Min Act: -0.0000

Data Index: 847701 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 4.0928. Min Range: -4.0928

Max Act: 3.5246. Min Act: -0.0001

Data Index: 672164 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 4.0928. Min Range: -4.0928

Max Act: 3.5287. Min Act: -0.0000

Data Index: 572434 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 4.0928. Min Range: -4.0928

Max Act: 3.4537. Min Act: -0.0000

Data Index: 422737 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 4.0928. Min Range: -4.0928

Max Act: 3.3331. Min Act: -0.0000

Data Index: 528427 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 4.0928. Min Range: -4.0928

Max Act: 3.1645. Min Act: -0.0000

Data Index: 1326878 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 4.0928. Min Range: -4.0928

Max Act: 3.3154. Min Act: -0.0000

Data Index: 175362 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 4.0928. Min Range: -4.0928

Max Act: 3.2786. Min Act: -0.0000

Data Index: 1275660 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 4.0928. Min Range: -4.0928

Max Act: 3.2858. Min Act: -0.0000

Data Index: 392190 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 4.0928. Min Range: -4.0928

Max Act: 3.4056. Min Act: -0.0000

Data Index: 992439 (C4 (Web Text))

Max Activating Token Index: 657