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

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

Neuron 504 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1301306 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0051. Min Act: -0.0002

Data Index: 756525 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1558150 (Python Code)

Max Activating Token Index: 141

Text #3

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0048. Min Act: -0.0002

Data Index: 1114366 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0046. Min Act: -0.0002

Data Index: 367144 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0046. Min Act: -0.0002

Data Index: 1094330 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0046. Min Act: -0.0002

Data Index: 465118 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0046. Min Act: -0.0002

Data Index: 389358 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0046. Min Act: -0.0002

Data Index: 303282 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1113026 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0044. Min Act: -0.0002

Data Index: 347003 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0044. Min Act: -0.0002

Data Index: 93782 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0044. Min Act: -0.0002

Data Index: 644581 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0044. Min Act: -0.0002

Data Index: 461635 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0043. Min Act: -0.0002

Data Index: 740496 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0043. Min Act: -0.0002

Data Index: 717594 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0043. Min Act: -0.0002

Data Index: 1087609 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0043. Min Act: -0.0002

Data Index: 536846 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0043. Min Act: -0.0002

Data Index: 766574 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0042. Min Act: -0.0002

Data Index: 864374 (C4 (Web Text))

Max Activating Token Index: 253