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

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

Neuron 3390 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1309730 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6042. Min Act: -0.0000

Data Index: 742803 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6107. Min Act: -0.0000

Data Index: 739679 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5443. Min Act: -0.0000

Data Index: 529426 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.4931. Min Act: -0.0000

Data Index: 1245102 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5353. Min Act: -0.0000

Data Index: 924415 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5200. Min Act: -0.0000

Data Index: 899960 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1001950 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1330005 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5221. Min Act: -0.0000

Data Index: 1338723 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5303. Min Act: -0.0000

Data Index: 491256 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.4775. Min Act: -0.0000

Data Index: 157498 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1315900 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1079777 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1104041 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.4326. Min Act: -0.0000

Data Index: 705796 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.4219. Min Act: -0.0000

Data Index: 1068048 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1191116 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1572043 (Python Code)

Max Activating Token Index: 75

Text #19

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.4198. Min Act: -0.0000

Data Index: 225608 (C4 (Web Text))

Max Activating Token Index: 58