Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2680 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.3852. Min Act: -0.0001

Data Index: 607805 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.3792. Min Act: -0.0000

Data Index: 906769 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.3636. Min Act: -0.0001

Data Index: 1359271 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.3600. Min Act: -0.0001

Data Index: 689217 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.3185. Min Act: -0.0000

Data Index: 348597 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2949. Min Act: -0.0001

Data Index: 1299033 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2928. Min Act: -0.0001

Data Index: 408700 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.3287. Min Act: -0.0000

Data Index: 375627 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.3258. Min Act: -0.0000

Data Index: 541113 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2990. Min Act: -0.0000

Data Index: 661064 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.3472. Min Act: -0.0000

Data Index: 867797 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2822. Min Act: -0.0000

Data Index: 824513 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2741. Min Act: -0.0000

Data Index: 501756 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2567. Min Act: -0.0000

Data Index: 385101 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2558. Min Act: -0.0001

Data Index: 105046 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2699. Min Act: -0.0001

Data Index: 879351 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2544. Min Act: -0.0000

Data Index: 125114 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2529. Min Act: -0.0001

Data Index: 736069 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1105688 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.3852. Min Range: -0.3852

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1014762 (C4 (Web Text))

Max Activating Token Index: 752