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

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

Neuron 2126 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2751. Min Act: 0.0000

Data Index: 242183 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2646. Min Act: -0.0000

Data Index: 137187 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2188. Min Act: 0.0000

Data Index: 59113 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2181. Min Act: -0.0000

Data Index: 931320 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1954. Min Act: -0.0000

Data Index: 552892 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2015. Min Act: -0.0000

Data Index: 559289 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2065. Min Act: -0.0000

Data Index: 886269 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1198027 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2133. Min Act: -0.0000

Data Index: 1265258 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2025. Min Act: -0.0000

Data Index: 2675 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1977. Min Act: -0.0000

Data Index: 363206 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1861. Min Act: 0.0000

Data Index: 1062727 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1148958 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1934. Min Act: -0.0000

Data Index: 395560 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1233294 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1970. Min Act: -0.0000

Data Index: 561748 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1939. Min Act: -0.0000

Data Index: 169733 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1781. Min Act: -0.0000

Data Index: 295731 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1904. Min Act: -0.0000

Data Index: 702934 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1769. Min Act: -0.0000

Data Index: 517500 (C4 (Web Text))

Max Activating Token Index: 65