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

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

Neuron 3452 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.6644. Min Act: -0.0002

Data Index: 42112 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.5886. Min Act: -0.0002

Data Index: 1020809 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.5733. Min Act: -0.0002

Data Index: 880371 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.5964. Min Act: -0.0002

Data Index: 486455 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.5587. Min Act: -0.0003

Data Index: 742591 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.5529. Min Act: -0.0002

Data Index: 926765 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.5041. Min Act: -0.0002

Data Index: 617289 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.4818. Min Act: -0.0002

Data Index: 1016033 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.5117. Min Act: -0.0002

Data Index: 1211801 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.5131. Min Act: -0.0002

Data Index: 1168901 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.5105. Min Act: -0.0002

Data Index: 901039 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.5006. Min Act: -0.0002

Data Index: 743611 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.4420. Min Act: -0.0002

Data Index: 274436 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.4708. Min Act: -0.0002

Data Index: 138532 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.4342. Min Act: -0.0002

Data Index: 816072 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.4499. Min Act: -0.0002

Data Index: 190200 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.4101. Min Act: -0.0002

Data Index: 1209405 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.4070. Min Act: -0.0002

Data Index: 802860 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.4057. Min Act: -0.0002

Data Index: 1258538 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.4191. Min Act: -0.0002

Data Index: 284623 (C4 (Web Text))

Max Activating Token Index: 875