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

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

Neuron 2117 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: 0.6446. Min Range: -0.6446

Max Act: 0.6446. Min Act: -0.0000

Data Index: 552381 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5772. Min Act: -0.0000

Data Index: 1064969 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5200. Min Act: -0.0000

Data Index: 302833 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5200. Min Act: -0.0000

Data Index: 78591 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1158240 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5108. Min Act: -0.0000

Data Index: 254751 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.4947. Min Act: -0.0000

Data Index: 756704 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.4643. Min Act: -0.0000

Data Index: 468110 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.5083. Min Act: -0.0000

Data Index: 215023 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.4884. Min Act: -0.0000

Data Index: 713095 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.4818. Min Act: -0.0000

Data Index: 837814 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1214302 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.4718. Min Act: -0.0000

Data Index: 331086 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.4491. Min Act: -0.0000

Data Index: 880164 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1070830 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.4514. Min Act: -0.0000

Data Index: 128062 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1283708 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.4486. Min Act: -0.0000

Data Index: 963539 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.4333. Min Act: -0.0000

Data Index: 863358 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.6446. Min Range: -0.6446

Max Act: 0.4448. Min Act: -0.0000

Data Index: 474822 (C4 (Web Text))

Max Activating Token Index: 81