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

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

Neuron 4459 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: 0.3079. Min Range: -0.3079

Max Act: 0.3079. Min Act: -0.0001

Data Index: 823520 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.3069. Min Act: -0.0001

Data Index: 356876 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2966. Min Act: -0.0001

Data Index: 58073 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2805. Min Act: -0.0001

Data Index: 462597 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.3008. Min Act: -0.0001

Data Index: 751549 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.3045. Min Act: -0.0001

Data Index: 370360 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2676. Min Act: -0.0001

Data Index: 669616 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2783. Min Act: -0.0001

Data Index: 1116670 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2147. Min Act: -0.0001

Data Index: 994292 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2589. Min Act: -0.0001

Data Index: 297754 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2499. Min Act: -0.0001

Data Index: 364899 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2660. Min Act: -0.0001

Data Index: 27204 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2461. Min Act: -0.0001

Data Index: 642039 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2301. Min Act: -0.0001

Data Index: 51819 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2252. Min Act: -0.0001

Data Index: 119051 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2332. Min Act: -0.0001

Data Index: 869297 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2542. Min Act: -0.0001

Data Index: 974857 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2328. Min Act: -0.0001

Data Index: 1296430 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2262. Min Act: -0.0001

Data Index: 51382 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2040. Min Act: -0.0001

Data Index: 791196 (C4 (Web Text))

Max Activating Token Index: 273