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

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

Neuron 2535 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: 1.5986. Min Range: -1.5986

Max Act: 1.5985. Min Act: -0.0002

Data Index: 941000 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.5986. Min Act: -0.0002

Data Index: 388164 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.5640. Min Act: -0.0002

Data Index: 1095766 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.5967. Min Act: -0.0002

Data Index: 603114 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.5570. Min Act: -0.0002

Data Index: 653626 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.5562. Min Act: -0.0002

Data Index: 560365 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.4480. Min Act: -0.0002

Data Index: 329755 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.5024. Min Act: -0.0002

Data Index: 115867 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.4588. Min Act: -0.0002

Data Index: 1272298 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.4273. Min Act: -0.0002

Data Index: 1253942 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.4138. Min Act: -0.0002

Data Index: 1102549 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.4225. Min Act: -0.0002

Data Index: 439697 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.4809. Min Act: -0.0002

Data Index: 463981 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.3852. Min Act: -0.0002

Data Index: 161776 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.4658. Min Act: -0.0002

Data Index: 66101 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.3923. Min Act: -0.0002

Data Index: 893723 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.4155. Min Act: -0.0002

Data Index: 583945 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.4116. Min Act: -0.0002

Data Index: 554759 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.4340. Min Act: -0.0002

Data Index: 1218803 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.4443. Min Act: -0.0002

Data Index: 394922 (C4 (Web Text))

Max Activating Token Index: 458