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

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

Neuron 1650 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: 0.0131. Min Range: -0.0131

Max Act: 0.0131. Min Act: -0.0006

Data Index: 922048 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1145776 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0106. Min Act: -0.0006

Data Index: 102525 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0109. Min Act: -0.0006

Data Index: 339301 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0106. Min Act: -0.0005

Data Index: 1184758 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0107. Min Act: -0.0006

Data Index: 534033 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0108. Min Act: -0.0005

Data Index: 1026138 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0108. Min Act: -0.0006

Data Index: 654886 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1145396 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0107. Min Act: -0.0006

Data Index: 409243 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0106. Min Act: -0.0006

Data Index: 715781 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0107. Min Act: -0.0006

Data Index: 543884 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1048185 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0104. Min Act: -0.0007

Data Index: 297267 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1132487 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0102. Min Act: -0.0006

Data Index: 468036 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1185256 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0102. Min Act: -0.0006

Data Index: 473766 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0103. Min Act: -0.0007

Data Index: 135902 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0103. Min Act: -0.0006

Data Index: 259988 (C4 (Web Text))

Max Activating Token Index: 535