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

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

Neuron 3216 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.3110. Min Act: -0.0001

Data Index: 894525 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.2921. Min Act: -0.0001

Data Index: 534696 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.3077. Min Act: -0.0000

Data Index: 194555 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.2868. Min Act: -0.0000

Data Index: 195749 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.2667. Min Act: -0.0001

Data Index: 429081 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.2788. Min Act: -0.0000

Data Index: 490400 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.2383. Min Act: -0.0000

Data Index: 227481 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1309770 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.2390. Min Act: -0.0001

Data Index: 274380 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.2287. Min Act: -0.0001

Data Index: 200948 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.1974. Min Act: -0.0000

Data Index: 945712 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.2091. Min Act: -0.0000

Data Index: 118205 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.2158. Min Act: -0.0000

Data Index: 216675 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.2015. Min Act: -0.0001

Data Index: 400950 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.1842. Min Act: -0.0000

Data Index: 816436 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.1958. Min Act: -0.0001

Data Index: 658417 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.1904. Min Act: -0.0000

Data Index: 230009 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.1934. Min Act: -0.0000

Data Index: 739425 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.1999. Min Act: -0.0001

Data Index: 281116 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.3110. Min Range: -0.3110

Max Act: 0.1942. Min Act: -0.0001

Data Index: 1096612 (C4 (Web Text))

Max Activating Token Index: 67