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

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

Neuron 116 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.6100. Min Act: -0.0001

Data Index: 1506856 (Python Code)

Max Activating Token Index: 693

Text #1

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5902. Min Act: -0.0001

Data Index: 1572670 (Python Code)

Max Activating Token Index: 1010

Text #2

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5410. Min Act: -0.0001

Data Index: 41097 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4952. Min Act: -0.0001

Data Index: 1539195 (Python Code)

Max Activating Token Index: 770

Text #4

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5225. Min Act: -0.0001

Data Index: 309567 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5502. Min Act: -0.0001

Data Index: 1486459 (Python Code)

Max Activating Token Index: 141

Text #6

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4953. Min Act: -0.0001

Data Index: 629381 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5148. Min Act: -0.0001

Data Index: 379170 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4988. Min Act: -0.0001

Data Index: 110363 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4822. Min Act: -0.0001

Data Index: 1637614 (Python Code)

Max Activating Token Index: 725

Text #10

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4771. Min Act: -0.0001

Data Index: 350044 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5073. Min Act: -0.0001

Data Index: 1532406 (Python Code)

Max Activating Token Index: 24

Text #12

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4887. Min Act: -0.0001

Data Index: 1240340 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4869. Min Act: -0.0001

Data Index: 921527 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4655. Min Act: -0.0001

Data Index: 840051 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4759. Min Act: -0.0001

Data Index: 170860 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4748. Min Act: -0.0001

Data Index: 395675 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4729. Min Act: -0.0001

Data Index: 1231488 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4588. Min Act: -0.0001

Data Index: 1331234 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3739. Min Act: -0.0001

Data Index: 536635 (C4 (Web Text))

Max Activating Token Index: 407