Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 24 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0072. Min Act: -0.0004

Data Index: 1234073 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0070. Min Act: -0.0003

Data Index: 176078 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0069. Min Act: -0.0004

Data Index: 237084 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0068. Min Act: -0.0004

Data Index: 965849 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0068. Min Act: -0.0004

Data Index: 1273165 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0069. Min Act: -0.0004

Data Index: 842049 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1156070 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0069. Min Act: -0.0003

Data Index: 821700 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0068. Min Act: -0.0004

Data Index: 442331 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0069. Min Act: -0.0003

Data Index: 698424 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0067. Min Act: -0.0004

Data Index: 365180 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0067. Min Act: -0.0004

Data Index: 662097 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0068. Min Act: -0.0004

Data Index: 124108 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0067. Min Act: -0.0004

Data Index: 204145 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0066. Min Act: -0.0004

Data Index: 526441 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0066. Min Act: -0.0004

Data Index: 1288900 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1351000 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0065. Min Act: -0.0004

Data Index: 318228 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0065. Min Act: -0.0004

Data Index: 81521 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.0072. Min Range: -0.0072

Max Act: 0.0065. Min Act: -0.0004

Data Index: 432580 (C4 (Web Text))

Max Activating Token Index: 652