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

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

Neuron 3848 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6545. Min Act: -0.0002

Data Index: 1143034 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6916. Min Act: -0.0002

Data Index: 853028 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.5148. Min Act: -0.0002

Data Index: 1280146 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6857. Min Act: -0.0002

Data Index: 882977 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6690. Min Act: -0.0002

Data Index: 1078032 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6568. Min Act: -0.0002

Data Index: 478393 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.5641. Min Act: -0.0002

Data Index: 839111 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.5777. Min Act: -0.0002

Data Index: 1316937 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.3810. Min Act: -0.0002

Data Index: 366751 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.3142. Min Act: -0.0002

Data Index: 1257893 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.3904. Min Act: -0.0002

Data Index: 976557 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.2185. Min Act: -0.0002

Data Index: 1189613 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.2653. Min Act: -0.0002

Data Index: 872656 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.2850. Min Act: -0.0002

Data Index: 162541 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.2537. Min Act: -0.0002

Data Index: 196582 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.2974. Min Act: -0.0002

Data Index: 6909 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.2520. Min Act: -0.0002

Data Index: 804907 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.2819. Min Act: -0.0002

Data Index: 1038535 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.2077. Min Act: -0.0002

Data Index: 853649 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.2713. Min Act: -0.0002

Data Index: 760577 (C4 (Web Text))

Max Activating Token Index: 926