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

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

Neuron 2575 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: 2.3851. Min Range: -2.3851

Max Act: 2.3851. Min Act: -0.0001

Data Index: 1175085 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.8430. Min Act: -0.0001

Data Index: 752609 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.8740. Min Act: -0.0000

Data Index: 1263375 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.7276. Min Act: -0.0000

Data Index: 722755 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.3567. Min Act: -0.0000

Data Index: 995174 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.2994. Min Act: -0.0000

Data Index: 214646 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.3258. Min Act: -0.0000

Data Index: 242833 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.2594. Min Act: -0.0000

Data Index: 1312886 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.3202. Min Act: -0.0000

Data Index: 707730 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.2724. Min Act: -0.0000

Data Index: 394757 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.2163. Min Act: -0.0000

Data Index: 1113630 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.2749. Min Act: -0.0000

Data Index: 524050 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.1920. Min Act: -0.0001

Data Index: 381721 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.1495. Min Act: -0.0000

Data Index: 204025 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.1284. Min Act: -0.0001

Data Index: 634833 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.1191. Min Act: -0.0000

Data Index: 370494 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.1107. Min Act: -0.0000

Data Index: 775180 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.1381. Min Act: -0.0001

Data Index: 399435 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.1730. Min Act: -0.0000

Data Index: 550303 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 2.3851. Min Range: -2.3851

Max Act: 1.2337. Min Act: -0.0000

Data Index: 1188977 (C4 (Web Text))

Max Activating Token Index: 522