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

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

Neuron 4475 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: 6.7520. Min Range: -6.7520

Max Act: 6.7520. Min Act: -0.0000

Data Index: 1340114 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 6.7520. Min Range: -6.7520

Max Act: 6.4270. Min Act: -0.0000

Data Index: 1148164 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 6.7520. Min Range: -6.7520

Max Act: 6.0591. Min Act: -0.0000

Data Index: 1279257 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 6.7520. Min Range: -6.7520

Max Act: 6.0403. Min Act: -0.0000

Data Index: 1098901 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 6.7520. Min Range: -6.7520

Max Act: 5.8508. Min Act: -0.0000

Data Index: 43870 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 6.7520. Min Range: -6.7520

Max Act: 5.6654. Min Act: -0.0000

Data Index: 790316 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 6.7520. Min Range: -6.7520

Max Act: 5.1852. Min Act: -0.0000

Data Index: 1130675 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 6.7520. Min Range: -6.7520

Max Act: 5.0991. Min Act: -0.0000

Data Index: 466347 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 6.7520. Min Range: -6.7520

Max Act: 5.0469. Min Act: -0.0000

Data Index: 1179200 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 6.7520. Min Range: -6.7520

Max Act: 5.0878. Min Act: -0.0000

Data Index: 786097 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 6.7520. Min Range: -6.7520

Max Act: 5.2283. Min Act: -0.0000

Data Index: 379430 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 6.7520. Min Range: -6.7520

Max Act: 4.9951. Min Act: -0.0000

Data Index: 447357 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 6.7520. Min Range: -6.7520

Max Act: 4.7815. Min Act: -0.0000

Data Index: 512666 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 6.7520. Min Range: -6.7520

Max Act: 4.7731. Min Act: -0.0000

Data Index: 77327 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 6.7520. Min Range: -6.7520

Max Act: 4.8703. Min Act: -0.0000

Data Index: 611793 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 6.7520. Min Range: -6.7520

Max Act: 4.6898. Min Act: -0.0000

Data Index: 615158 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 6.7520. Min Range: -6.7520

Max Act: 4.8275. Min Act: -0.0000

Data Index: 702779 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 6.7520. Min Range: -6.7520

Max Act: 4.8054. Min Act: -0.0000

Data Index: 183958 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 6.7520. Min Range: -6.7520

Max Act: 4.7924. Min Act: -0.0000

Data Index: 34092 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 6.7520. Min Range: -6.7520

Max Act: 4.6776. Min Act: -0.0000

Data Index: 592755 (C4 (Web Text))

Max Activating Token Index: 990