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

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

Neuron 83 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: 1.5087. Min Range: -1.5087

Max Act: 1.5087. Min Act: -0.0001

Data Index: 237248 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.4423. Min Act: -0.0001

Data Index: 1275477 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.4707. Min Act: -0.0001

Data Index: 698879 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.4406. Min Act: -0.0001

Data Index: 669050 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.3647. Min Act: -0.0001

Data Index: 1299230 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.3314. Min Act: -0.0001

Data Index: 269861 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.3655. Min Act: -0.0001

Data Index: 400 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.2000. Min Act: -0.0001

Data Index: 199863 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.1896. Min Act: -0.0001

Data Index: 305009 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.3386. Min Act: -0.0001

Data Index: 941921 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.2378. Min Act: -0.0001

Data Index: 399991 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.3162. Min Act: -0.0001

Data Index: 1141857 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.2425. Min Act: -0.0001

Data Index: 466648 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.1951. Min Act: -0.0001

Data Index: 278656 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.0815. Min Act: -0.0001

Data Index: 193561 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.1854. Min Act: -0.0001

Data Index: 1330203 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.2059. Min Act: -0.0001

Data Index: 569271 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.1863. Min Act: -0.0001

Data Index: 1009783 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.1015. Min Act: -0.0001

Data Index: 866074 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.0689. Min Act: -0.0001

Data Index: 1035140 (C4 (Web Text))

Max Activating Token Index: 393