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

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

Neuron 1015 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.6725. Min Act: -0.0000

Data Index: 735348 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.7584. Min Act: 0.0000

Data Index: 1306475 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.6173. Min Act: -0.0000

Data Index: 759957 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.5152. Min Act: 0.0000

Data Index: 1058300 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.5325. Min Act: -0.0000

Data Index: 1197460 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.4431. Min Act: -0.0000

Data Index: 634365 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.4126. Min Act: -0.0000

Data Index: 112473 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.4892. Min Act: 0.0000

Data Index: 240823 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.3982. Min Act: 0.0000

Data Index: 1307507 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.4092. Min Act: 0.0000

Data Index: 544307 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.2714. Min Act: -0.0000

Data Index: 1322102 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.2015. Min Act: 0.0000

Data Index: 399030 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.2557. Min Act: -0.0000

Data Index: 710572 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.2785. Min Act: -0.0000

Data Index: 657615 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.2605. Min Act: -0.0000

Data Index: 287301 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.3198. Min Act: 0.0000

Data Index: 729245 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.2716. Min Act: 0.0000

Data Index: 88090 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.2456. Min Act: -0.0000

Data Index: 519761 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.1911. Min Act: 0.0000

Data Index: 130077 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 1.7584. Min Range: -1.7584

Max Act: 1.1410. Min Act: -0.0000

Data Index: 436422 (C4 (Web Text))

Max Activating Token Index: 34