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

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

Neuron 5260 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.3287. Min Act: -0.0000

Data Index: 138159 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.3226. Min Act: -0.0000

Data Index: 240804 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.3161. Min Act: -0.0000

Data Index: 50380 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1326869 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.3110. Min Act: -0.0000

Data Index: 619095 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2906. Min Act: -0.0000

Data Index: 628229 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2735. Min Act: -0.0000

Data Index: 212401 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2559. Min Act: -0.0000

Data Index: 974101 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2410. Min Act: -0.0000

Data Index: 879480 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2168. Min Act: -0.0000

Data Index: 883201 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2049. Min Act: -0.0000

Data Index: 902043 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2153. Min Act: -0.0000

Data Index: 1139008 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.1989. Min Act: -0.0000

Data Index: 55273 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.1973. Min Act: -0.0000

Data Index: 701175 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.1929. Min Act: -0.0000

Data Index: 657463 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2030. Min Act: -0.0000

Data Index: 687443 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2105. Min Act: -0.0000

Data Index: 694768 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1337772 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1148094 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.3287. Min Range: -0.3287

Max Act: 0.1880. Min Act: -0.0000

Data Index: 1272803 (C4 (Web Text))

Max Activating Token Index: 687