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

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

Neuron 2848 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3646. Min Act: -0.0001

Data Index: 1019228 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3411. Min Act: -0.0001

Data Index: 1179996 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3294. Min Act: -0.0001

Data Index: 188678 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3100. Min Act: -0.0001

Data Index: 180153 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.3107. Min Act: -0.0001

Data Index: 994544 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2987. Min Act: -0.0001

Data Index: 1265956 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2760. Min Act: -0.0001

Data Index: 774814 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2858. Min Act: -0.0001

Data Index: 857014 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2900. Min Act: -0.0001

Data Index: 1088740 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2799. Min Act: -0.0001

Data Index: 580621 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2854. Min Act: -0.0001

Data Index: 762471 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2855. Min Act: -0.0001

Data Index: 18502 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2937. Min Act: -0.0001

Data Index: 256919 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2836. Min Act: -0.0001

Data Index: 298043 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2820. Min Act: -0.0001

Data Index: 380786 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2784. Min Act: -0.0001

Data Index: 735708 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2677. Min Act: -0.0001

Data Index: 918924 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2681. Min Act: -0.0001

Data Index: 925048 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2820. Min Act: -0.0001

Data Index: 1212397 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.3646. Min Range: -0.3646

Max Act: 0.2821. Min Act: -0.0001

Data Index: 52964 (C4 (Web Text))

Max Activating Token Index: 1010