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

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

Neuron 5687 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7970. Min Act: -0.0000

Data Index: 419439 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7048. Min Act: -0.0000

Data Index: 1425599 (Python Code)

Max Activating Token Index: 429

Text #2

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7721. Min Act: -0.0000

Data Index: 1439943 (Python Code)

Max Activating Token Index: 805

Text #3

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.6671. Min Act: -0.0000

Data Index: 437824 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.6544. Min Act: 0.0000

Data Index: 72121 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.6005. Min Act: -0.0000

Data Index: 23315 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5984. Min Act: -0.0000

Data Index: 562514 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.6384. Min Act: -0.0000

Data Index: 1436036 (Python Code)

Max Activating Token Index: 618

Text #8

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5684. Min Act: -0.0000

Data Index: 669283 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5502. Min Act: 0.0000

Data Index: 53577 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5105. Min Act: -0.0000

Data Index: 880594 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1172836 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.4991. Min Act: -0.0000

Data Index: 342690 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.4668. Min Act: 0.0000

Data Index: 1010680 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1601218 (Python Code)

Max Activating Token Index: 105

Text #15

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.4825. Min Act: 0.0000

Data Index: 1127652 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.4747. Min Act: 0.0000

Data Index: 102490 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.4782. Min Act: -0.0000

Data Index: 274797 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1098614 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.4313. Min Act: -0.0000

Data Index: 533562 (C4 (Web Text))

Max Activating Token Index: 1004