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

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

Neuron 197 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.4042. Min Act: -0.0000

Data Index: 572020 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.3133. Min Act: -0.0000

Data Index: 1206712 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.1880. Min Act: -0.0000

Data Index: 1042709 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.3962. Min Act: -0.0000

Data Index: 377968 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.1762. Min Act: -0.0000

Data Index: 543296 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.1549. Min Act: -0.0000

Data Index: 18036 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.0668. Min Act: -0.0000

Data Index: 562414 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.0370. Min Act: -0.0000

Data Index: 937688 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 1.4042. Min Range: -1.4042

Max Act: 0.9334. Min Act: -0.0000

Data Index: 1002315 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.0663. Min Act: -0.0000

Data Index: 749260 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.0027. Min Act: -0.0000

Data Index: 388380 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 1.4042. Min Range: -1.4042

Max Act: 0.9689. Min Act: -0.0000

Data Index: 284133 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.0169. Min Act: -0.0000

Data Index: 521509 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 1.4042. Min Range: -1.4042

Max Act: 0.9905. Min Act: -0.0000

Data Index: 1220245 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.0100. Min Act: -0.0000

Data Index: 676275 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 1.4042. Min Range: -1.4042

Max Act: 0.9582. Min Act: -0.0000

Data Index: 849661 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 1.4042. Min Range: -1.4042

Max Act: 0.9548. Min Act: -0.0000

Data Index: 312216 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 1.4042. Min Range: -1.4042

Max Act: 0.9784. Min Act: -0.0000

Data Index: 708877 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 1.4042. Min Range: -1.4042

Max Act: 0.8961. Min Act: -0.0000

Data Index: 378783 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 1.4042. Min Range: -1.4042

Max Act: 0.8923. Min Act: -0.0000

Data Index: 126352 (C4 (Web Text))

Max Activating Token Index: 131