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

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

Neuron 3189 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: 1.4942. Min Range: -1.4942

Max Act: 1.4942. Min Act: -0.0001

Data Index: 653995 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.2254. Min Act: -0.0001

Data Index: 168990 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.2790. Min Act: -0.0001

Data Index: 383481 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.3101. Min Act: -0.0001

Data Index: 1181706 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.0611. Min Act: -0.0001

Data Index: 667296 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.2049. Min Act: -0.0001

Data Index: 631746 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.0867. Min Act: -0.0001

Data Index: 1040899 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 1.4942. Min Range: -1.4942

Max Act: 0.9934. Min Act: -0.0001

Data Index: 1093104 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.0530. Min Act: -0.0001

Data Index: 1159789 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.1203. Min Act: -0.0001

Data Index: 1179008 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.0613. Min Act: -0.0001

Data Index: 62636 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.0930. Min Act: -0.0001

Data Index: 60279 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.0633. Min Act: -0.0001

Data Index: 1035560 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.1137. Min Act: -0.0001

Data Index: 302341 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 1.4942. Min Range: -1.4942

Max Act: 0.9860. Min Act: -0.0001

Data Index: 2792 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 1.4942. Min Range: -1.4942

Max Act: 0.9779. Min Act: -0.0001

Data Index: 194004 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.0307. Min Act: -0.0001

Data Index: 301181 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.0519. Min Act: -0.0001

Data Index: 44660 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 1.4942. Min Range: -1.4942

Max Act: 1.0137. Min Act: -0.0001

Data Index: 130074 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 1.4942. Min Range: -1.4942

Max Act: 0.9652. Min Act: -0.0001

Data Index: 386055 (C4 (Web Text))

Max Activating Token Index: 765