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

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

Neuron 3793 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0786. Min Range: -2.0786

Max Act: 2.0786. Min Act: -0.0000

Data Index: 857460 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 2.0786. Min Range: -2.0786

Max Act: 2.0222. Min Act: -0.0000

Data Index: 888573 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 2.0786. Min Range: -2.0786

Max Act: 1.9816. Min Act: -0.0000

Data Index: 950078 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 2.0786. Min Range: -2.0786

Max Act: 1.7974. Min Act: -0.0000

Data Index: 82245 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 2.0786. Min Range: -2.0786

Max Act: 1.7540. Min Act: -0.0000

Data Index: 52961 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 2.0786. Min Range: -2.0786

Max Act: 1.6730. Min Act: -0.0000

Data Index: 660291 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 2.0786. Min Range: -2.0786

Max Act: 1.6064. Min Act: 0.0001

Data Index: 398467 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 2.0786. Min Range: -2.0786

Max Act: 1.5703. Min Act: -0.0000

Data Index: 285569 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 2.0786. Min Range: -2.0786

Max Act: 1.5926. Min Act: -0.0000

Data Index: 292842 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 2.0786. Min Range: -2.0786

Max Act: 1.5890. Min Act: -0.0000

Data Index: 1034436 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 2.0786. Min Range: -2.0786

Max Act: 1.5166. Min Act: -0.0000

Data Index: 447218 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 2.0786. Min Range: -2.0786

Max Act: 1.5080. Min Act: -0.0001

Data Index: 778153 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 2.0786. Min Range: -2.0786

Max Act: 1.4996. Min Act: 0.0001

Data Index: 1166255 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 2.0786. Min Range: -2.0786

Max Act: 1.5154. Min Act: 0.0000

Data Index: 1284560 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 2.0786. Min Range: -2.0786

Max Act: 1.5094. Min Act: -0.0000

Data Index: 268907 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 2.0786. Min Range: -2.0786

Max Act: 1.5094. Min Act: 0.0000

Data Index: 457460 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 2.0786. Min Range: -2.0786

Max Act: 1.5072. Min Act: -0.0001

Data Index: 594971 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 2.0786. Min Range: -2.0786

Max Act: 1.5046. Min Act: -0.0000

Data Index: 1341366 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 2.0786. Min Range: -2.0786

Max Act: 1.4853. Min Act: -0.0000

Data Index: 484031 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 2.0786. Min Range: -2.0786

Max Act: 1.5143. Min Act: -0.0000

Data Index: 1135150 (C4 (Web Text))

Max Activating Token Index: 109