Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2353 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0175. Min Act: -0.0002

Data Index: 521172 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0150. Min Act: -0.0002

Data Index: 688096 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0144. Min Act: -0.0002

Data Index: 609103 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0127. Min Act: -0.0002

Data Index: 901803 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0128. Min Act: -0.0002

Data Index: 207705 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0116. Min Act: -0.0002

Data Index: 364 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0114. Min Act: -0.0002

Data Index: 52062 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0108. Min Act: -0.0002

Data Index: 528265 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0104. Min Act: -0.0002

Data Index: 143214 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0110. Min Act: -0.0002

Data Index: 77734 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0112. Min Act: -0.0002

Data Index: 148974 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0108. Min Act: -0.0002

Data Index: 542762 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0106. Min Act: -0.0002

Data Index: 899582 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0104. Min Act: -0.0002

Data Index: 1285080 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0104. Min Act: -0.0002

Data Index: 497855 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0099. Min Act: -0.0002

Data Index: 1283732 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0100. Min Act: -0.0002

Data Index: 1306129 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0100. Min Act: -0.0002

Data Index: 991166 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0098. Min Act: -0.0002

Data Index: 938292 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0103. Min Act: -0.0002

Data Index: 1205171 (C4 (Web Text))

Max Activating Token Index: 592