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

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

Neuron 5529 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4046. Min Range: -4.4046

Max Act: 4.4046. Min Act: -0.0000

Data Index: 919060 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 4.4046. Min Range: -4.4046

Max Act: 3.9079. Min Act: -0.0000

Data Index: 570884 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 4.4046. Min Range: -4.4046

Max Act: 3.9498. Min Act: -0.0000

Data Index: 1146904 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 4.4046. Min Range: -4.4046

Max Act: 4.1091. Min Act: -0.0000

Data Index: 149945 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 4.4046. Min Range: -4.4046

Max Act: 3.6760. Min Act: -0.0000

Data Index: 805593 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 4.4046. Min Range: -4.4046

Max Act: 3.5206. Min Act: -0.0000

Data Index: 745657 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 4.4046. Min Range: -4.4046

Max Act: 3.6530. Min Act: -0.0000

Data Index: 18650 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 4.4046. Min Range: -4.4046

Max Act: 3.5372. Min Act: -0.0000

Data Index: 1137944 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 4.4046. Min Range: -4.4046

Max Act: 3.5503. Min Act: -0.0000

Data Index: 1125817 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 4.4046. Min Range: -4.4046

Max Act: 3.5682. Min Act: -0.0000

Data Index: 1039251 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 4.4046. Min Range: -4.4046

Max Act: 3.2435. Min Act: -0.0000

Data Index: 1266462 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 4.4046. Min Range: -4.4046

Max Act: 3.3822. Min Act: -0.0000

Data Index: 663115 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 4.4046. Min Range: -4.4046

Max Act: 3.3270. Min Act: -0.0000

Data Index: 460505 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 4.4046. Min Range: -4.4046

Max Act: 3.1645. Min Act: -0.0000

Data Index: 255236 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 4.4046. Min Range: -4.4046

Max Act: 3.3049. Min Act: -0.0000

Data Index: 541126 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 4.4046. Min Range: -4.4046

Max Act: 3.2896. Min Act: -0.0000

Data Index: 501492 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 4.4046. Min Range: -4.4046

Max Act: 3.2833. Min Act: -0.0000

Data Index: 557237 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 4.4046. Min Range: -4.4046

Max Act: 3.2609. Min Act: -0.0000

Data Index: 905719 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 4.4046. Min Range: -4.4046

Max Act: 3.1227. Min Act: -0.0000

Data Index: 1274377 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 4.4046. Min Range: -4.4046

Max Act: 3.2519. Min Act: -0.0000

Data Index: 843284 (C4 (Web Text))

Max Activating Token Index: 872