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

Dataset: The Pile

Neuron 1321 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.4624. Min Act: -0.0000

Data Index: 504014 (The Pile)

Max Activating Token Index: 667

Text #1

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.5068. Min Act: -0.0000

Data Index: 1767047 (The Pile)

Max Activating Token Index: 302

Text #2

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.4945. Min Act: -0.0000

Data Index: 1044155 (The Pile)

Max Activating Token Index: 203

Text #3

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.4607. Min Act: -0.0000

Data Index: 1500573 (The Pile)

Max Activating Token Index: 442

Text #4

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.5069. Min Act: -0.0000

Data Index: 1876819 (The Pile)

Max Activating Token Index: 350

Text #5

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.4087. Min Act: -0.0000

Data Index: 1278581 (The Pile)

Max Activating Token Index: 228

Text #6

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.3182. Min Act: -0.0000

Data Index: 1899742 (The Pile)

Max Activating Token Index: 601

Text #7

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.2899. Min Act: -0.0000

Data Index: 1757940 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.2792. Min Act: -0.0000

Data Index: 405550 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.3532. Min Act: -0.0000

Data Index: 185439 (The Pile)

Max Activating Token Index: 728

Text #10

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.2624. Min Act: -0.0000

Data Index: 800773 (The Pile)

Max Activating Token Index: 481

Text #11

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.3053. Min Act: -0.0000

Data Index: 1859752 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.3320. Min Act: -0.0000

Data Index: 716841 (The Pile)

Max Activating Token Index: 972

Text #13

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.3161. Min Act: -0.0000

Data Index: 253113 (The Pile)

Max Activating Token Index: 623

Text #14

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.3066. Min Act: -0.0000

Data Index: 1025026 (The Pile)

Max Activating Token Index: 906

Text #15

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.3390. Min Act: -0.0000

Data Index: 1022090 (The Pile)

Max Activating Token Index: 957

Text #16

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.2746. Min Act: -0.0000

Data Index: 654510 (The Pile)

Max Activating Token Index: 198

Text #17

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.2930. Min Act: -0.0000

Data Index: 1950262 (The Pile)

Max Activating Token Index: 175

Text #18

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.2880. Min Act: -0.0000

Data Index: 112955 (The Pile)

Max Activating Token Index: 208

Text #19

Max Range: 1.5069. Min Range: -1.5069

Max Act: 1.2878. Min Act: -0.0000

Data Index: 1372648 (The Pile)

Max Activating Token Index: 975