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

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

Neuron 3498 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7139. Min Range: -2.7139

Max Act: 2.7139. Min Act: -0.0000

Data Index: 269100 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 2.7139. Min Range: -2.7139

Max Act: 2.2284. Min Act: -0.0000

Data Index: 993046 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 2.7139. Min Range: -2.7139

Max Act: 2.3005. Min Act: -0.0000

Data Index: 1027531 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 2.7139. Min Range: -2.7139

Max Act: 1.9241. Min Act: -0.0000

Data Index: 678575 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 2.7139. Min Range: -2.7139

Max Act: 2.0175. Min Act: -0.0000

Data Index: 90654 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 2.7139. Min Range: -2.7139

Max Act: 2.0492. Min Act: -0.0000

Data Index: 705784 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 2.7139. Min Range: -2.7139

Max Act: 1.9403. Min Act: -0.0000

Data Index: 596791 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 2.7139. Min Range: -2.7139

Max Act: 1.8144. Min Act: -0.0000

Data Index: 438098 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 2.7139. Min Range: -2.7139

Max Act: 1.9059. Min Act: -0.0000

Data Index: 352329 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 2.7139. Min Range: -2.7139

Max Act: 1.8969. Min Act: -0.0000

Data Index: 578852 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 2.7139. Min Range: -2.7139

Max Act: 1.9699. Min Act: -0.0000

Data Index: 1291742 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 2.7139. Min Range: -2.7139

Max Act: 1.7966. Min Act: -0.0000

Data Index: 299240 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 2.7139. Min Range: -2.7139

Max Act: 1.7762. Min Act: -0.0000

Data Index: 189977 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 2.7139. Min Range: -2.7139

Max Act: 1.7971. Min Act: -0.0000

Data Index: 989442 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 2.7139. Min Range: -2.7139

Max Act: 1.4774. Min Act: -0.0000

Data Index: 1208028 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 2.7139. Min Range: -2.7139

Max Act: 1.7409. Min Act: -0.0000

Data Index: 279206 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 2.7139. Min Range: -2.7139

Max Act: 1.6865. Min Act: -0.0000

Data Index: 283551 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 2.7139. Min Range: -2.7139

Max Act: 1.6517. Min Act: -0.0000

Data Index: 1245312 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 2.7139. Min Range: -2.7139

Max Act: 1.4615. Min Act: -0.0000

Data Index: 1082972 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 2.7139. Min Range: -2.7139

Max Act: 1.5280. Min Act: -0.0000

Data Index: 1112897 (C4 (Web Text))

Max Activating Token Index: 690