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

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

Neuron 2410 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.3224. Min Act: -0.0002

Data Index: 273052 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.2969. Min Act: -0.0002

Data Index: 1159249 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.2865. Min Act: -0.0002

Data Index: 1184898 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.2758. Min Act: -0.0002

Data Index: 868247 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.2132. Min Act: -0.0002

Data Index: 1208662 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1908. Min Act: -0.0002

Data Index: 824024 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1983. Min Act: -0.0002

Data Index: 665338 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.2134. Min Act: -0.0002

Data Index: 921951 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1820. Min Act: -0.0002

Data Index: 811580 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1710. Min Act: -0.0002

Data Index: 261889 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1937. Min Act: -0.0002

Data Index: 463494 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1943. Min Act: -0.0002

Data Index: 503271 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1565. Min Act: -0.0002

Data Index: 851270 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1602. Min Act: -0.0003

Data Index: 314924 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1651. Min Act: -0.0002

Data Index: 1228212 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1582. Min Act: -0.0002

Data Index: 659863 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1498. Min Act: -0.0002

Data Index: 1348262 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1413. Min Act: -0.0002

Data Index: 1283811 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1447. Min Act: -0.0002

Data Index: 485597 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 1.3224. Min Range: -1.3224

Max Act: 1.1479. Min Act: -0.0002

Data Index: 299035 (C4 (Web Text))

Max Activating Token Index: 36