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

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

Neuron 4849 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: 0.0101. Min Range: -0.0101

Max Act: 0.0099. Min Act: -0.0002

Data Index: 463451 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0101. Min Act: -0.0002

Data Index: 121847 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0099. Min Act: -0.0002

Data Index: 478020 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0098. Min Act: -0.0002

Data Index: 1081801 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0096. Min Act: -0.0002

Data Index: 1335699 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0093. Min Act: -0.0002

Data Index: 719650 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0092. Min Act: -0.0002

Data Index: 260342 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0091. Min Act: -0.0002

Data Index: 437086 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0091. Min Act: -0.0002

Data Index: 1281226 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0002

Data Index: 191178 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1152283 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0002

Data Index: 34881 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0002

Data Index: 529768 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1092350 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0089. Min Act: -0.0002

Data Index: 558966 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1356217 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0088. Min Act: -0.0002

Data Index: 921236 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1067977 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0002

Data Index: 383409 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0088. Min Act: -0.0002

Data Index: 708596 (C4 (Web Text))

Max Activating Token Index: 185