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

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

Neuron 2925 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3841. Min Act: -0.0003

Data Index: 1148404 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3393. Min Act: -0.0003

Data Index: 778938 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3345. Min Act: -0.0003

Data Index: 406571 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2874. Min Act: -0.0003

Data Index: 1105184 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2999. Min Act: -0.0003

Data Index: 579627 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2963. Min Act: -0.0003

Data Index: 232138 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3012. Min Act: -0.0003

Data Index: 1301962 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2916. Min Act: -0.0003

Data Index: 73368 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3000. Min Act: -0.0003

Data Index: 72381 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2931. Min Act: -0.0003

Data Index: 1279379 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2776. Min Act: -0.0003

Data Index: 1141116 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2896. Min Act: -0.0003

Data Index: 1158585 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2505. Min Act: -0.0003

Data Index: 1316072 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2893. Min Act: -0.0003

Data Index: 850802 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.3054. Min Act: -0.0003

Data Index: 527579 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2853. Min Act: -0.0003

Data Index: 1310266 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2746. Min Act: -0.0003

Data Index: 265597 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2773. Min Act: -0.0003

Data Index: 492763 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2975. Min Act: -0.0003

Data Index: 703880 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.3841. Min Range: -0.3841

Max Act: 0.2881. Min Act: -0.0003

Data Index: 43467 (C4 (Web Text))

Max Activating Token Index: 776