Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3591 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.0142. Min Range: -4.0142

Max Act: 4.0142. Min Act: -0.0000

Data Index: 23758 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 4.0142. Min Range: -4.0142

Max Act: 3.2253. Min Act: -0.0000

Data Index: 327207 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 4.0142. Min Range: -4.0142

Max Act: 3.4540. Min Act: -0.0000

Data Index: 1085943 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 4.0142. Min Range: -4.0142

Max Act: 3.2986. Min Act: -0.0000

Data Index: 1318425 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 4.0142. Min Range: -4.0142

Max Act: 2.8906. Min Act: -0.0000

Data Index: 953020 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 4.0142. Min Range: -4.0142

Max Act: 2.7054. Min Act: -0.0000

Data Index: 1123457 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 4.0142. Min Range: -4.0142

Max Act: 2.1124. Min Act: -0.0000

Data Index: 539410 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 4.0142. Min Range: -4.0142

Max Act: 1.6401. Min Act: -0.0000

Data Index: 1244819 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 4.0142. Min Range: -4.0142

Max Act: 0.8228. Min Act: -0.0000

Data Index: 1351405 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 4.0142. Min Range: -4.0142

Max Act: 0.9987. Min Act: -0.0000

Data Index: 815223 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 4.0142. Min Range: -4.0142

Max Act: 0.7836. Min Act: 0.0000

Data Index: 504066 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 4.0142. Min Range: -4.0142

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1348776 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 4.0142. Min Range: -4.0142

Max Act: 0.6749. Min Act: -0.0000

Data Index: 230651 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 4.0142. Min Range: -4.0142

Max Act: 0.6596. Min Act: -0.0000

Data Index: 324257 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 4.0142. Min Range: -4.0142

Max Act: 0.6573. Min Act: -0.0000

Data Index: 453670 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 4.0142. Min Range: -4.0142

Max Act: 0.6499. Min Act: -0.0000

Data Index: 214872 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 4.0142. Min Range: -4.0142

Max Act: 0.6012. Min Act: 0.0000

Data Index: 1013513 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 4.0142. Min Range: -4.0142

Max Act: 0.5712. Min Act: -0.0000

Data Index: 745028 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 4.0142. Min Range: -4.0142

Max Act: 0.5879. Min Act: -0.0000

Data Index: 550764 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 4.0142. Min Range: -4.0142

Max Act: 0.5833. Min Act: -0.0000

Data Index: 132404 (C4 (Web Text))

Max Activating Token Index: 207