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

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

Neuron 3867 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0085. Min Act: -0.0003

Data Index: 680543 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0078. Min Act: -0.0003

Data Index: 1594189 (Python Code)

Max Activating Token Index: 23

Text #2

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0079. Min Act: -0.0003

Data Index: 801193 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0077. Min Act: -0.0003

Data Index: 707180 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0073. Min Act: -0.0003

Data Index: 339142 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1520940 (Python Code)

Max Activating Token Index: 569

Text #6

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1091365 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0068. Min Act: -0.0003

Data Index: 341566 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1432048 (Python Code)

Max Activating Token Index: 511

Text #9

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0066. Min Act: -0.0003

Data Index: 237236 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1382417 (Python Code)

Max Activating Token Index: 479

Text #11

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0064. Min Act: -0.0004

Data Index: 236097 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1408511 (Python Code)

Max Activating Token Index: 39

Text #13

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1521632 (Python Code)

Max Activating Token Index: 71

Text #14

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0063. Min Act: -0.0003

Data Index: 1060491 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0064. Min Act: -0.0003

Data Index: 311228 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0063. Min Act: -0.0003

Data Index: 163196 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0060. Min Act: -0.0003

Data Index: 409549 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0062. Min Act: -0.0003

Data Index: 88709 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.0085. Min Range: -0.0085

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1631244 (Python Code)

Max Activating Token Index: 250