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

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

Neuron 2259 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.7170. Min Act: -0.0002

Data Index: 835850 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6883. Min Act: -0.0002

Data Index: 1284034 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6973. Min Act: -0.0002

Data Index: 286903 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6867. Min Act: -0.0002

Data Index: 316547 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.7303. Min Act: -0.0002

Data Index: 72879 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6146. Min Act: -0.0002

Data Index: 1011011 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5573. Min Act: -0.0002

Data Index: 970036 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5669. Min Act: -0.0002

Data Index: 525467 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5374. Min Act: -0.0002

Data Index: 1181405 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5823. Min Act: -0.0002

Data Index: 687219 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5070. Min Act: -0.0002

Data Index: 549077 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5246. Min Act: -0.0002

Data Index: 207635 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.4609. Min Act: -0.0002

Data Index: 1298913 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.4834. Min Act: -0.0002

Data Index: 176435 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5441. Min Act: -0.0002

Data Index: 490287 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.4421. Min Act: -0.0002

Data Index: 903363 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.4676. Min Act: -0.0002

Data Index: 182636 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.4387. Min Act: -0.0002

Data Index: 897776 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.4400. Min Act: -0.0002

Data Index: 1491245 (Python Code)

Max Activating Token Index: 626

Text #19

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.4271. Min Act: -0.0002

Data Index: 1385024 (Python Code)

Max Activating Token Index: 543