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

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

Neuron 2882 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.7827. Min Act: -0.0000

Data Index: 1049358 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.2812. Min Act: -0.0000

Data Index: 876863 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.2997. Min Act: -0.0000

Data Index: 1319542 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 4.7827. Min Range: -4.7827

Max Act: 3.7305. Min Act: -0.0000

Data Index: 1000702 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 4.7827. Min Range: -4.7827

Max Act: 3.7940. Min Act: -0.0000

Data Index: 588753 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 4.7827. Min Range: -4.7827

Max Act: 3.7131. Min Act: -0.0000

Data Index: 289219 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 4.7827. Min Range: -4.7827

Max Act: 3.5140. Min Act: -0.0000

Data Index: 663407 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 4.7827. Min Range: -4.7827

Max Act: 3.6719. Min Act: -0.0000

Data Index: 671915 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 4.7827. Min Range: -4.7827

Max Act: 3.5903. Min Act: -0.0000

Data Index: 1197244 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 4.7827. Min Range: -4.7827

Max Act: 3.5395. Min Act: -0.0000

Data Index: 1347971 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 4.7827. Min Range: -4.7827

Max Act: 3.3722. Min Act: -0.0000

Data Index: 62190 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 4.7827. Min Range: -4.7827

Max Act: 3.5389. Min Act: -0.0000

Data Index: 1214002 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 4.7827. Min Range: -4.7827

Max Act: 3.4910. Min Act: -0.0000

Data Index: 220274 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 4.7827. Min Range: -4.7827

Max Act: 3.3879. Min Act: -0.0000

Data Index: 1205099 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 4.7827. Min Range: -4.7827

Max Act: 3.3985. Min Act: -0.0000

Data Index: 796012 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 4.7827. Min Range: -4.7827

Max Act: 3.1876. Min Act: -0.0000

Data Index: 1241249 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 4.7827. Min Range: -4.7827

Max Act: 3.2504. Min Act: -0.0000

Data Index: 705039 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 4.7827. Min Range: -4.7827

Max Act: 3.1945. Min Act: -0.0000

Data Index: 908561 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 4.7827. Min Range: -4.7827

Max Act: 3.0336. Min Act: -0.0000

Data Index: 53574 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 4.7827. Min Range: -4.7827

Max Act: 3.0093. Min Act: -0.0000

Data Index: 799959 (C4 (Web Text))

Max Activating Token Index: 197