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

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

Neuron 2711 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.6861. Min Act: -0.0001

Data Index: 216143 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.6814. Min Act: -0.0001

Data Index: 226420 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5460. Min Act: -0.0001

Data Index: 58223 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5909. Min Act: -0.0001

Data Index: 592129 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5502. Min Act: -0.0001

Data Index: 692033 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5044. Min Act: -0.0001

Data Index: 463440 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5188. Min Act: -0.0001

Data Index: 1159274 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4723. Min Act: -0.0001

Data Index: 1347641 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4408. Min Act: -0.0001

Data Index: 1309848 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5102. Min Act: -0.0001

Data Index: 902370 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5015. Min Act: -0.0001

Data Index: 932735 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.5505. Min Act: -0.0001

Data Index: 13021 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4997. Min Act: -0.0001

Data Index: 718214 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4851. Min Act: -0.0001

Data Index: 1329496 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4835. Min Act: -0.0001

Data Index: 1171250 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4922. Min Act: -0.0001

Data Index: 348153 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4790. Min Act: -0.0001

Data Index: 787389 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4888. Min Act: -0.0001

Data Index: 531066 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4804. Min Act: -0.0001

Data Index: 427049 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.6861. Min Range: -0.6861

Max Act: 0.4823. Min Act: -0.0001

Data Index: 678787 (C4 (Web Text))

Max Activating Token Index: 253