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

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

Neuron 1881 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.5732. Min Act: -0.0000

Data Index: 846833 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.6802. Min Act: -0.0000

Data Index: 1189461 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.5223. Min Act: -0.0000

Data Index: 36709 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.4747. Min Act: -0.0000

Data Index: 747770 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.3337. Min Act: -0.0000

Data Index: 1265747 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.3113. Min Act: -0.0000

Data Index: 1014432 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.2907. Min Act: -0.0000

Data Index: 1289965 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.2668. Min Act: -0.0000

Data Index: 107944 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.2770. Min Act: -0.0000

Data Index: 143112 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.0805. Min Act: -0.0000

Data Index: 1019706 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.0392. Min Act: -0.0000

Data Index: 384029 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.0166. Min Act: -0.0000

Data Index: 834053 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 2.6802. Min Range: -2.6802

Max Act: 1.9145. Min Act: -0.0000

Data Index: 1325612 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.1146. Min Act: -0.0000

Data Index: 920609 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.2383. Min Act: -0.0000

Data Index: 252933 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.0237. Min Act: -0.0000

Data Index: 34963 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.0020. Min Act: -0.0000

Data Index: 456316 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.3735. Min Act: -0.0000

Data Index: 1127161 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 2.6802. Min Range: -2.6802

Max Act: 2.0078. Min Act: -0.0000

Data Index: 329017 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 2.6802. Min Range: -2.6802

Max Act: 1.9753. Min Act: -0.0000

Data Index: 447723 (C4 (Web Text))

Max Activating Token Index: 564