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

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

Neuron 3241 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: 0.0162. Min Range: -0.0162

Max Act: 0.0162. Min Act: -0.0003

Data Index: 732929 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0144. Min Act: -0.0003

Data Index: 237173 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0140. Min Act: -0.0003

Data Index: 189566 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0135. Min Act: -0.0003

Data Index: 677686 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0130. Min Act: -0.0003

Data Index: 1017564 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0125. Min Act: -0.0004

Data Index: 1263577 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0121. Min Act: -0.0003

Data Index: 406008 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0120. Min Act: -0.0003

Data Index: 359816 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0116. Min Act: -0.0003

Data Index: 576579 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0111. Min Act: -0.0003

Data Index: 203785 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0104. Min Act: -0.0003

Data Index: 43535 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0105. Min Act: -0.0003

Data Index: 555161 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0098. Min Act: -0.0003

Data Index: 129092 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0100. Min Act: -0.0003

Data Index: 685931 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0103. Min Act: -0.0003

Data Index: 516476 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0100. Min Act: -0.0004

Data Index: 838675 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0103. Min Act: -0.0003

Data Index: 1132009 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0099. Min Act: -0.0003

Data Index: 791054 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0101. Min Act: -0.0004

Data Index: 1255670 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0094. Min Act: -0.0003

Data Index: 204142 (C4 (Web Text))

Max Activating Token Index: 570