Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2325 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.8736. Min Act: -0.0002

Data Index: 125555 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7503. Min Act: -0.0001

Data Index: 1024010 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7485. Min Act: -0.0002

Data Index: 1309755 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6997. Min Act: -0.0002

Data Index: 11296 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7382. Min Act: -0.0002

Data Index: 882183 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7296. Min Act: -0.0002

Data Index: 68549 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6884. Min Act: -0.0002

Data Index: 553898 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7399. Min Act: -0.0002

Data Index: 1123776 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7168. Min Act: -0.0002

Data Index: 728858 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6952. Min Act: -0.0002

Data Index: 19381 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6474. Min Act: -0.0001

Data Index: 805114 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6628. Min Act: -0.0002

Data Index: 8020 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6810. Min Act: -0.0002

Data Index: 1274029 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6803. Min Act: -0.0002

Data Index: 192064 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6781. Min Act: -0.0001

Data Index: 286461 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6781. Min Act: -0.0001

Data Index: 689899 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6665. Min Act: -0.0002

Data Index: 1145047 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.5867. Min Act: -0.0002

Data Index: 1076479 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6267. Min Act: -0.0001

Data Index: 1259305 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6867. Min Act: -0.0001

Data Index: 1507351 (Python Code)

Max Activating Token Index: 779