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

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

Neuron 4765 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1137. Min Range: -2.1137

Max Act: 2.1137. Min Act: -0.0001

Data Index: 203171 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 2.1137. Min Range: -2.1137

Max Act: 2.0930. Min Act: -0.0001

Data Index: 1209209 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 2.1137. Min Range: -2.1137

Max Act: 1.7173. Min Act: -0.0001

Data Index: 536419 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 2.1137. Min Range: -2.1137

Max Act: 1.9868. Min Act: -0.0001

Data Index: 859099 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 2.1137. Min Range: -2.1137

Max Act: 1.8141. Min Act: -0.0001

Data Index: 226291 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 2.1137. Min Range: -2.1137

Max Act: 1.8964. Min Act: -0.0001

Data Index: 273901 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 2.1137. Min Range: -2.1137

Max Act: 1.7432. Min Act: -0.0001

Data Index: 1141976 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 2.1137. Min Range: -2.1137

Max Act: 1.9092. Min Act: -0.0000

Data Index: 508652 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 2.1137. Min Range: -2.1137

Max Act: 1.7902. Min Act: -0.0001

Data Index: 994094 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 2.1137. Min Range: -2.1137

Max Act: 1.6349. Min Act: -0.0001

Data Index: 418107 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 2.1137. Min Range: -2.1137

Max Act: 1.8404. Min Act: -0.0001

Data Index: 998934 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 2.1137. Min Range: -2.1137

Max Act: 1.8220. Min Act: -0.0001

Data Index: 1065067 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 2.1137. Min Range: -2.1137

Max Act: 1.7033. Min Act: -0.0001

Data Index: 1126056 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 2.1137. Min Range: -2.1137

Max Act: 1.5780. Min Act: -0.0001

Data Index: 441278 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 2.1137. Min Range: -2.1137

Max Act: 1.8171. Min Act: -0.0000

Data Index: 166877 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 2.1137. Min Range: -2.1137

Max Act: 1.7288. Min Act: -0.0000

Data Index: 589431 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 2.1137. Min Range: -2.1137

Max Act: 1.6173. Min Act: -0.0001

Data Index: 2428 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 2.1137. Min Range: -2.1137

Max Act: 1.5279. Min Act: -0.0001

Data Index: 551859 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 2.1137. Min Range: -2.1137

Max Act: 1.6631. Min Act: -0.0001

Data Index: 309856 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 2.1137. Min Range: -2.1137

Max Act: 1.5174. Min Act: -0.0001

Data Index: 1042417 (C4 (Web Text))

Max Activating Token Index: 600