Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 443 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0159. Min Act: -0.0006

Data Index: 124824 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0107. Min Act: -0.0006

Data Index: 647328 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0108. Min Act: -0.0006

Data Index: 1164596 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0106. Min Act: -0.0006

Data Index: 199245 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0103. Min Act: -0.0006

Data Index: 281925 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0097. Min Act: -0.0006

Data Index: 409329 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0090. Min Act: -0.0006

Data Index: 437579 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0092. Min Act: -0.0006

Data Index: 884748 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0087. Min Act: -0.0006

Data Index: 95030 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0089. Min Act: -0.0006

Data Index: 1094026 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0086. Min Act: -0.0006

Data Index: 676342 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0088. Min Act: -0.0006

Data Index: 1210930 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0086. Min Act: -0.0006

Data Index: 427036 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0084. Min Act: -0.0006

Data Index: 270512 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0083. Min Act: -0.0006

Data Index: 506394 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0081. Min Act: -0.0006

Data Index: 233939 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0081. Min Act: -0.0006

Data Index: 389933 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0084. Min Act: -0.0006

Data Index: 1126021 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0084. Min Act: -0.0006

Data Index: 514232 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0084. Min Act: -0.0006

Data Index: 537308 (C4 (Web Text))

Max Activating Token Index: 879