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

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

Neuron 2895 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: 1.9583. Min Range: -1.9583

Max Act: 1.9583. Min Act: -0.0003

Data Index: 858805 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 1.9583. Min Range: -1.9583

Max Act: 1.7129. Min Act: -0.0002

Data Index: 1048929 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 1.9583. Min Range: -1.9583

Max Act: 1.6779. Min Act: -0.0003

Data Index: 165472 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 1.9583. Min Range: -1.9583

Max Act: 1.6685. Min Act: -0.0002

Data Index: 1169080 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 1.9583. Min Range: -1.9583

Max Act: 1.6001. Min Act: -0.0002

Data Index: 937956 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 1.9583. Min Range: -1.9583

Max Act: 1.5837. Min Act: -0.0002

Data Index: 1140438 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 1.9583. Min Range: -1.9583

Max Act: 1.5089. Min Act: -0.0002

Data Index: 1312458 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 1.9583. Min Range: -1.9583

Max Act: 1.5025. Min Act: -0.0002

Data Index: 468498 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 1.9583. Min Range: -1.9583

Max Act: 1.4739. Min Act: -0.0003

Data Index: 1011186 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 1.9583. Min Range: -1.9583

Max Act: 1.4588. Min Act: -0.0002

Data Index: 1276931 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 1.9583. Min Range: -1.9583

Max Act: 1.4493. Min Act: -0.0002

Data Index: 1015993 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 1.9583. Min Range: -1.9583

Max Act: 1.4360. Min Act: -0.0002

Data Index: 354590 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 1.9583. Min Range: -1.9583

Max Act: 1.4158. Min Act: -0.0002

Data Index: 543877 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 1.9583. Min Range: -1.9583

Max Act: 1.4069. Min Act: -0.0002

Data Index: 32547 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 1.9583. Min Range: -1.9583

Max Act: 1.4383. Min Act: -0.0002

Data Index: 717391 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 1.9583. Min Range: -1.9583

Max Act: 1.4052. Min Act: -0.0002

Data Index: 939876 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 1.9583. Min Range: -1.9583

Max Act: 1.4369. Min Act: -0.0002

Data Index: 522939 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 1.9583. Min Range: -1.9583

Max Act: 1.4693. Min Act: -0.0002

Data Index: 314650 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 1.9583. Min Range: -1.9583

Max Act: 1.3973. Min Act: -0.0002

Data Index: 287276 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 1.9583. Min Range: -1.9583

Max Act: 1.4104. Min Act: -0.0002

Data Index: 266364 (C4 (Web Text))

Max Activating Token Index: 211