Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1187 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4780. Min Range: -1.4780

Max Act: 1.4780. Min Act: -0.0000

Data Index: 587756 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 1.4780. Min Range: -1.4780

Max Act: 1.3136. Min Act: -0.0001

Data Index: 769160 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 1.4780. Min Range: -1.4780

Max Act: 1.1924. Min Act: -0.0000

Data Index: 224390 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 1.4780. Min Range: -1.4780

Max Act: 1.1121. Min Act: -0.0001

Data Index: 870920 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 1.4780. Min Range: -1.4780

Max Act: 1.1654. Min Act: -0.0001

Data Index: 1157405 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 1.4780. Min Range: -1.4780

Max Act: 1.1003. Min Act: -0.0000

Data Index: 34099 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 1.4780. Min Range: -1.4780

Max Act: 0.8685. Min Act: -0.0001

Data Index: 983944 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 1.4780. Min Range: -1.4780

Max Act: 1.0165. Min Act: -0.0000

Data Index: 1323622 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 1.4780. Min Range: -1.4780

Max Act: 1.0410. Min Act: -0.0000

Data Index: 1332745 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 1.4780. Min Range: -1.4780

Max Act: 0.9610. Min Act: -0.0000

Data Index: 912409 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 1.4780. Min Range: -1.4780

Max Act: 1.0779. Min Act: -0.0001

Data Index: 1093803 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 1.4780. Min Range: -1.4780

Max Act: 1.0409. Min Act: -0.0001

Data Index: 480282 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 1.4780. Min Range: -1.4780

Max Act: 0.9409. Min Act: -0.0001

Data Index: 537188 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 1.4780. Min Range: -1.4780

Max Act: 0.9370. Min Act: -0.0000

Data Index: 809374 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 1.4780. Min Range: -1.4780

Max Act: 0.9853. Min Act: -0.0001

Data Index: 697837 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 1.4780. Min Range: -1.4780

Max Act: 0.9353. Min Act: -0.0001

Data Index: 1316702 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 1.4780. Min Range: -1.4780

Max Act: 0.9978. Min Act: -0.0000

Data Index: 684952 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 1.4780. Min Range: -1.4780

Max Act: 0.9325. Min Act: -0.0000

Data Index: 1158233 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 1.4780. Min Range: -1.4780

Max Act: 0.9575. Min Act: -0.0000

Data Index: 566378 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 1.4780. Min Range: -1.4780

Max Act: 0.9507. Min Act: -0.0000

Data Index: 269775 (C4 (Web Text))

Max Activating Token Index: 979