Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 35 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0101. Min Act: -0.0004

Data Index: 764205 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0100. Min Act: -0.0004

Data Index: 1439160 (Python Code)

Max Activating Token Index: 72

Text #2

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0099. Min Act: -0.0004

Data Index: 84173 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0095. Min Act: -0.0004

Data Index: 1143318 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0095. Min Act: -0.0004

Data Index: 208214 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0096. Min Act: -0.0004

Data Index: 1002515 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0093. Min Act: -0.0004

Data Index: 330077 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0095. Min Act: -0.0005

Data Index: 101947 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0095. Min Act: -0.0004

Data Index: 361249 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0095. Min Act: -0.0005

Data Index: 798766 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0095. Min Act: -0.0004

Data Index: 677499 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0094. Min Act: -0.0004

Data Index: 1527365 (Python Code)

Max Activating Token Index: 925

Text #12

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0094. Min Act: -0.0005

Data Index: 1208909 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0093. Min Act: -0.0005

Data Index: 450813 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0091. Min Act: -0.0004

Data Index: 692300 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0093. Min Act: -0.0005

Data Index: 713444 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0091. Min Act: -0.0004

Data Index: 225450 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0091. Min Act: -0.0004

Data Index: 250144 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0092. Min Act: -0.0004

Data Index: 1233618 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0005

Data Index: 692336 (C4 (Web Text))

Max Activating Token Index: 624