Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2036 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0123. Min Act: -0.0006

Data Index: 723984 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0120. Min Act: -0.0006

Data Index: 491556 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0117. Min Act: -0.0006

Data Index: 674325 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0117. Min Act: -0.0006

Data Index: 549706 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0116. Min Act: -0.0006

Data Index: 292417 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0111. Min Act: -0.0006

Data Index: 1174324 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0111. Min Act: -0.0006

Data Index: 715609 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1126308 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0109. Min Act: -0.0006

Data Index: 768085 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0108. Min Act: -0.0006

Data Index: 901538 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0107. Min Act: -0.0006

Data Index: 699216 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0106. Min Act: -0.0006

Data Index: 925162 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0106. Min Act: -0.0005

Data Index: 839236 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0104. Min Act: -0.0006

Data Index: 954669 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0107. Min Act: -0.0006

Data Index: 373233 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0104. Min Act: -0.0006

Data Index: 96742 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0101. Min Act: -0.0006

Data Index: 660581 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0096. Min Act: -0.0006

Data Index: 1130703 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0096. Min Act: -0.0006

Data Index: 1358004 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0100. Min Act: -0.0006

Data Index: 507954 (C4 (Web Text))

Max Activating Token Index: 940