Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1847 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.3183. Min Act: -0.0001

Data Index: 423705 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2994. Min Act: -0.0001

Data Index: 420555 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2871. Min Act: -0.0000

Data Index: 1244508 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2774. Min Act: -0.0001

Data Index: 197153 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2751. Min Act: -0.0001

Data Index: 224736 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2662. Min Act: -0.0000

Data Index: 261711 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2737. Min Act: -0.0000

Data Index: 575149 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2710. Min Act: -0.0000

Data Index: 737900 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2779. Min Act: -0.0000

Data Index: 21184 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2621. Min Act: -0.0000

Data Index: 468455 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2621. Min Act: -0.0001

Data Index: 941781 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2615. Min Act: -0.0000

Data Index: 436000 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2583. Min Act: -0.0001

Data Index: 1445470 (Python Code)

Max Activating Token Index: 953

Text #13

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2507. Min Act: -0.0001

Data Index: 529277 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2403. Min Act: -0.0001

Data Index: 1276046 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2588. Min Act: -0.0001

Data Index: 392545 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1237278 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2671. Min Act: -0.0000

Data Index: 739841 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2556. Min Act: -0.0001

Data Index: 74112 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2498. Min Act: -0.0001

Data Index: 611064 (C4 (Web Text))

Max Activating Token Index: 766