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

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

Neuron 2756 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.7913. Min Act: -0.0000

Data Index: 1565670 (Python Code)

Max Activating Token Index: 890

Text #1

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.5612. Min Act: -0.0000

Data Index: 906675 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.4856. Min Act: -0.0000

Data Index: 656191 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.3352. Min Act: -0.0000

Data Index: 659339 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.4168. Min Act: -0.0000

Data Index: 1190250 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.3893. Min Act: -0.0000

Data Index: 886409 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.1574. Min Act: -0.0000

Data Index: 786716 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.1351. Min Act: -0.0000

Data Index: 880218 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.1601. Min Act: -0.0000

Data Index: 632170 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.1187. Min Act: -0.0000

Data Index: 1423483 (Python Code)

Max Activating Token Index: 94

Text #10

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.0549. Min Act: -0.0000

Data Index: 1335644 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.0517. Min Act: -0.0000

Data Index: 458606 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.0568. Min Act: -0.0000

Data Index: 755215 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 1.7913. Min Range: -1.7913

Max Act: 1.0688. Min Act: -0.0000

Data Index: 996140 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 1.7913. Min Range: -1.7913

Max Act: 0.9101. Min Act: -0.0000

Data Index: 866566 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 1.7913. Min Range: -1.7913

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1589889 (Python Code)

Max Activating Token Index: 1007

Text #16

Max Range: 1.7913. Min Range: -1.7913

Max Act: 0.9998. Min Act: -0.0000

Data Index: 232673 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 1.7913. Min Range: -1.7913

Max Act: 0.9992. Min Act: -0.0000

Data Index: 1000552 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 1.7913. Min Range: -1.7913

Max Act: 0.9938. Min Act: -0.0000

Data Index: 366973 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 1.7913. Min Range: -1.7913

Max Act: 0.9841. Min Act: -0.0000

Data Index: 7373 (C4 (Web Text))

Max Activating Token Index: 418