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

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

Neuron 3568 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4117. Min Range: -1.4117

Max Act: 1.4117. Min Act: -0.0001

Data Index: 1026187 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 1.4117. Min Range: -1.4117

Max Act: 1.2362. Min Act: -0.0001

Data Index: 1020399 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 1.4117. Min Range: -1.4117

Max Act: 1.2138. Min Act: -0.0001

Data Index: 164942 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 1.4117. Min Range: -1.4117

Max Act: 1.2135. Min Act: -0.0001

Data Index: 1327707 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 1.4117. Min Range: -1.4117

Max Act: 1.2133. Min Act: -0.0001

Data Index: 286589 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 1.4117. Min Range: -1.4117

Max Act: 1.0486. Min Act: -0.0000

Data Index: 1070199 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 1.4117. Min Range: -1.4117

Max Act: 1.1054. Min Act: -0.0000

Data Index: 560983 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 1.4117. Min Range: -1.4117

Max Act: 1.0453. Min Act: -0.0001

Data Index: 1238939 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 1.4117. Min Range: -1.4117

Max Act: 0.9771. Min Act: -0.0001

Data Index: 557020 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 1.4117. Min Range: -1.4117

Max Act: 0.9873. Min Act: -0.0001

Data Index: 941214 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 1.4117. Min Range: -1.4117

Max Act: 1.0403. Min Act: -0.0001

Data Index: 1168495 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 1.4117. Min Range: -1.4117

Max Act: 1.0675. Min Act: -0.0001

Data Index: 469069 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 1.4117. Min Range: -1.4117

Max Act: 0.9669. Min Act: -0.0000

Data Index: 322447 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 1.4117. Min Range: -1.4117

Max Act: 0.9855. Min Act: -0.0000

Data Index: 922420 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 1.4117. Min Range: -1.4117

Max Act: 0.9341. Min Act: -0.0000

Data Index: 707944 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 1.4117. Min Range: -1.4117

Max Act: 0.9418. Min Act: -0.0001

Data Index: 14394 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 1.4117. Min Range: -1.4117

Max Act: 0.9314. Min Act: -0.0001

Data Index: 1045820 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 1.4117. Min Range: -1.4117

Max Act: 1.0000. Min Act: -0.0000

Data Index: 565510 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 1.4117. Min Range: -1.4117

Max Act: 0.9704. Min Act: -0.0000

Data Index: 779795 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 1.4117. Min Range: -1.4117

Max Act: 0.8053. Min Act: -0.0001

Data Index: 89787 (C4 (Web Text))

Max Activating Token Index: 315