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

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

Neuron 2117 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.2049. Min Range: -3.2049

Max Act: 3.2049. Min Act: -0.0000

Data Index: 652826 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 3.2049. Min Range: -3.2049

Max Act: 2.7615. Min Act: -0.0000

Data Index: 777480 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 3.2049. Min Range: -3.2049

Max Act: 2.6906. Min Act: -0.0001

Data Index: 791102 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 3.2049. Min Range: -3.2049

Max Act: 2.3901. Min Act: -0.0000

Data Index: 1072199 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 3.2049. Min Range: -3.2049

Max Act: 2.6784. Min Act: -0.0000

Data Index: 1078583 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 3.2049. Min Range: -3.2049

Max Act: 2.2665. Min Act: -0.0001

Data Index: 1128713 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 3.2049. Min Range: -3.2049

Max Act: 2.4667. Min Act: -0.0001

Data Index: 607221 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 3.2049. Min Range: -3.2049

Max Act: 2.4450. Min Act: -0.0000

Data Index: 738262 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 3.2049. Min Range: -3.2049

Max Act: 2.3088. Min Act: -0.0000

Data Index: 839458 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 3.2049. Min Range: -3.2049

Max Act: 2.3327. Min Act: -0.0001

Data Index: 247658 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 3.2049. Min Range: -3.2049

Max Act: 1.9810. Min Act: -0.0001

Data Index: 48567 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 3.2049. Min Range: -3.2049

Max Act: 2.1825. Min Act: -0.0000

Data Index: 588882 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 3.2049. Min Range: -3.2049

Max Act: 2.0386. Min Act: -0.0001

Data Index: 1330231 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 3.2049. Min Range: -3.2049

Max Act: 2.1440. Min Act: -0.0001

Data Index: 781577 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 3.2049. Min Range: -3.2049

Max Act: 2.0094. Min Act: -0.0001

Data Index: 1005295 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 3.2049. Min Range: -3.2049

Max Act: 2.0234. Min Act: -0.0001

Data Index: 1011840 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 3.2049. Min Range: -3.2049

Max Act: 2.1078. Min Act: -0.0001

Data Index: 85075 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 3.2049. Min Range: -3.2049

Max Act: 2.1111. Min Act: -0.0000

Data Index: 400632 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 3.2049. Min Range: -3.2049

Max Act: 2.0948. Min Act: -0.0000

Data Index: 1034870 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 3.2049. Min Range: -3.2049

Max Act: 2.1082. Min Act: -0.0001

Data Index: 242281 (C4 (Web Text))

Max Activating Token Index: 446