Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1221 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.5115. Min Act: -0.0001

Data Index: 753286 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4338. Min Act: -0.0001

Data Index: 947883 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4191. Min Act: -0.0001

Data Index: 208845 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.4232. Min Act: -0.0001

Data Index: 94671 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.3930. Min Act: -0.0001

Data Index: 73525 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.3665. Min Act: -0.0001

Data Index: 683105 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.3773. Min Act: -0.0001

Data Index: 1045067 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.3789. Min Act: -0.0001

Data Index: 840185 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.3694. Min Act: -0.0001

Data Index: 476708 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.3364. Min Act: -0.0001

Data Index: 528799 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.3569. Min Act: -0.0001

Data Index: 1051002 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.3501. Min Act: -0.0001

Data Index: 142435 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.3366. Min Act: -0.0001

Data Index: 972594 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.3275. Min Act: -0.0001

Data Index: 390405 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.3288. Min Act: -0.0001

Data Index: 1022092 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.3089. Min Act: -0.0001

Data Index: 649829 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.2904. Min Act: -0.0001

Data Index: 162272 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.3181. Min Act: -0.0001

Data Index: 203270 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.3056. Min Act: -0.0001

Data Index: 911528 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.5115. Min Range: -0.5115

Max Act: 0.3141. Min Act: -0.0001

Data Index: 1329615 (C4 (Web Text))

Max Activating Token Index: 4