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

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

Neuron 1546 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.7159. Min Act: -0.0001

Data Index: 951916 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6869. Min Act: -0.0001

Data Index: 263134 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6870. Min Act: -0.0001

Data Index: 148657 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6688. Min Act: -0.0001

Data Index: 881100 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6309. Min Act: -0.0001

Data Index: 1336968 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6419. Min Act: -0.0001

Data Index: 1299724 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6179. Min Act: -0.0001

Data Index: 38882 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6341. Min Act: -0.0001

Data Index: 128041 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6331. Min Act: -0.0001

Data Index: 1155518 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6486. Min Act: -0.0001

Data Index: 300461 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6275. Min Act: -0.0001

Data Index: 1115261 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6040. Min Act: -0.0001

Data Index: 290981 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6327. Min Act: -0.0001

Data Index: 127722 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.5891. Min Act: -0.0001

Data Index: 23161 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6091. Min Act: -0.0001

Data Index: 122506 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6044. Min Act: -0.0001

Data Index: 1233646 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6233. Min Act: -0.0001

Data Index: 160185 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.6002. Min Act: -0.0001

Data Index: 585383 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.5772. Min Act: -0.0001

Data Index: 1002479 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.7159. Min Range: -0.7159

Max Act: 0.5761. Min Act: -0.0001

Data Index: 920953 (C4 (Web Text))

Max Activating Token Index: 936