Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2462 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1430. Min Range: -2.1430

Max Act: 2.1430. Min Act: -0.0000

Data Index: 501509 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 2.1430. Min Range: -2.1430

Max Act: 1.9845. Min Act: -0.0000

Data Index: 1180202 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 2.1430. Min Range: -2.1430

Max Act: 1.7700. Min Act: -0.0000

Data Index: 291117 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 2.1430. Min Range: -2.1430

Max Act: 1.8388. Min Act: -0.0000

Data Index: 846337 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 2.1430. Min Range: -2.1430

Max Act: 2.0247. Min Act: -0.0000

Data Index: 192075 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 2.1430. Min Range: -2.1430

Max Act: 1.7816. Min Act: -0.0000

Data Index: 1111796 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 2.1430. Min Range: -2.1430

Max Act: 1.9657. Min Act: -0.0000

Data Index: 756897 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 2.1430. Min Range: -2.1430

Max Act: 1.9487. Min Act: -0.0000

Data Index: 95360 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 2.1430. Min Range: -2.1430

Max Act: 1.8023. Min Act: -0.0000

Data Index: 358681 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 2.1430. Min Range: -2.1430

Max Act: 1.7859. Min Act: -0.0000

Data Index: 844641 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 2.1430. Min Range: -2.1430

Max Act: 1.7739. Min Act: -0.0000

Data Index: 1118129 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 2.1430. Min Range: -2.1430

Max Act: 1.6349. Min Act: -0.0000

Data Index: 287086 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 2.1430. Min Range: -2.1430

Max Act: 1.6859. Min Act: -0.0000

Data Index: 1184359 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 2.1430. Min Range: -2.1430

Max Act: 1.5956. Min Act: -0.0000

Data Index: 1356431 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 2.1430. Min Range: -2.1430

Max Act: 1.6700. Min Act: -0.0000

Data Index: 250530 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 2.1430. Min Range: -2.1430

Max Act: 1.6538. Min Act: -0.0000

Data Index: 1071212 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 2.1430. Min Range: -2.1430

Max Act: 1.6261. Min Act: -0.0000

Data Index: 531180 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 2.1430. Min Range: -2.1430

Max Act: 1.6108. Min Act: -0.0000

Data Index: 483341 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 2.1430. Min Range: -2.1430

Max Act: 1.6188. Min Act: -0.0000

Data Index: 631155 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 2.1430. Min Range: -2.1430

Max Act: 1.6036. Min Act: -0.0000

Data Index: 759291 (C4 (Web Text))

Max Activating Token Index: 61