Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2721 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.2402. Min Act: -0.0001

Data Index: 838267 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.2227. Min Act: -0.0001

Data Index: 491695 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.2214. Min Act: -0.0001

Data Index: 92420 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1978. Min Act: -0.0001

Data Index: 761310 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.2052. Min Act: -0.0001

Data Index: 499878 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1891. Min Act: -0.0001

Data Index: 634008 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1877. Min Act: -0.0001

Data Index: 225608 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1935. Min Act: -0.0001

Data Index: 1174051 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1842. Min Act: -0.0001

Data Index: 1493085 (Python Code)

Max Activating Token Index: 989

Text #9

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1703. Min Act: -0.0001

Data Index: 225459 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1697. Min Act: -0.0001

Data Index: 244347 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1681. Min Act: -0.0001

Data Index: 1324092 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1675. Min Act: -0.0001

Data Index: 30254 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1686. Min Act: -0.0001

Data Index: 464682 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1666. Min Act: -0.0001

Data Index: 671922 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1631. Min Act: -0.0001

Data Index: 726402 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1621. Min Act: -0.0001

Data Index: 259018 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1521. Min Act: -0.0001

Data Index: 988752 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1582. Min Act: -0.0001

Data Index: 1019974 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.2402. Min Range: -0.2402

Max Act: 0.1683. Min Act: -0.0001

Data Index: 981150 (C4 (Web Text))

Max Activating Token Index: 152