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

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

Neuron 1306 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1965. Min Range: -6.1965

Max Act: 6.1965. Min Act: -0.0000

Data Index: 18346 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 6.1965. Min Range: -6.1965

Max Act: 6.0494. Min Act: -0.0000

Data Index: 358925 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 6.1965. Min Range: -6.1965

Max Act: 5.8067. Min Act: -0.0000

Data Index: 489340 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 6.1965. Min Range: -6.1965

Max Act: 5.5108. Min Act: -0.0000

Data Index: 1058560 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 6.1965. Min Range: -6.1965

Max Act: 5.4767. Min Act: -0.0000

Data Index: 319376 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 6.1965. Min Range: -6.1965

Max Act: 5.6310. Min Act: -0.0000

Data Index: 252636 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 6.1965. Min Range: -6.1965

Max Act: 5.6079. Min Act: -0.0000

Data Index: 301624 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 6.1965. Min Range: -6.1965

Max Act: 5.3922. Min Act: -0.0000

Data Index: 1308776 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 6.1965. Min Range: -6.1965

Max Act: 5.3825. Min Act: -0.0000

Data Index: 1070328 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 6.1965. Min Range: -6.1965

Max Act: 5.5396. Min Act: -0.0000

Data Index: 1088743 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 6.1965. Min Range: -6.1965

Max Act: 5.3723. Min Act: -0.0000

Data Index: 1135813 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 6.1965. Min Range: -6.1965

Max Act: 5.5584. Min Act: -0.0000

Data Index: 237499 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 6.1965. Min Range: -6.1965

Max Act: 5.3574. Min Act: -0.0000

Data Index: 488139 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 6.1965. Min Range: -6.1965

Max Act: 5.6761. Min Act: -0.0000

Data Index: 501256 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 6.1965. Min Range: -6.1965

Max Act: 5.2313. Min Act: -0.0000

Data Index: 228008 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 6.1965. Min Range: -6.1965

Max Act: 5.3945. Min Act: -0.0000

Data Index: 77159 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 6.1965. Min Range: -6.1965

Max Act: 5.1848. Min Act: -0.0000

Data Index: 1263825 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 6.1965. Min Range: -6.1965

Max Act: 5.3776. Min Act: -0.0000

Data Index: 567066 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 6.1965. Min Range: -6.1965

Max Act: 5.3660. Min Act: -0.0000

Data Index: 526304 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 6.1965. Min Range: -6.1965

Max Act: 5.3820. Min Act: -0.0000

Data Index: 1218024 (C4 (Web Text))

Max Activating Token Index: 951