Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1049 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.4544. Min Act: -0.0001

Data Index: 126251 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.4357. Min Act: -0.0001

Data Index: 145642 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.4275. Min Act: -0.0001

Data Index: 278769 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.4127. Min Act: -0.0001

Data Index: 1358996 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.4681. Min Act: -0.0001

Data Index: 950084 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.4042. Min Act: -0.0001

Data Index: 916969 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.4030. Min Act: -0.0001

Data Index: 894251 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.4279. Min Act: -0.0001

Data Index: 324101 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.4282. Min Act: -0.0001

Data Index: 1279928 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.4213. Min Act: -0.0001

Data Index: 455185 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.4114. Min Act: -0.0001

Data Index: 554770 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.3969. Min Act: -0.0001

Data Index: 1305152 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.3862. Min Act: -0.0001

Data Index: 237352 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.3988. Min Act: -0.0001

Data Index: 496237 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.4111. Min Act: -0.0001

Data Index: 369559 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.3984. Min Act: -0.0001

Data Index: 80763 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.4249. Min Act: -0.0001

Data Index: 1067344 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.4124. Min Act: -0.0001

Data Index: 515280 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.3903. Min Act: -0.0001

Data Index: 309471 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 0.4681. Min Range: -0.4681

Max Act: 0.3752. Min Act: -0.0001

Data Index: 841220 (C4 (Web Text))

Max Activating Token Index: 428