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

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

Neuron 784 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4982. Min Act: -0.0001

Data Index: 749271 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4436. Min Act: -0.0001

Data Index: 646396 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4172. Min Act: -0.0001

Data Index: 571602 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3645. Min Act: -0.0001

Data Index: 374650 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3706. Min Act: -0.0001

Data Index: 919007 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3466. Min Act: -0.0001

Data Index: 636273 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3416. Min Act: -0.0001

Data Index: 93737 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3198. Min Act: -0.0001

Data Index: 1127659 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3076. Min Act: -0.0001

Data Index: 1013038 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3259. Min Act: -0.0001

Data Index: 588243 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3174. Min Act: -0.0001

Data Index: 1272274 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3111. Min Act: -0.0001

Data Index: 390577 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3016. Min Act: -0.0001

Data Index: 1063471 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.2914. Min Act: -0.0001

Data Index: 1130683 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.2897. Min Act: -0.0001

Data Index: 1010909 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.2797. Min Act: -0.0001

Data Index: 210438 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.2846. Min Act: -0.0001

Data Index: 723435 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.2701. Min Act: -0.0001

Data Index: 448683 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.2841. Min Act: -0.0001

Data Index: 1294872 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.2799. Min Act: -0.0001

Data Index: 398377 (C4 (Web Text))

Max Activating Token Index: 202