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

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

Neuron 6066 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4921. Min Act: -0.0000

Data Index: 1515110 (Python Code)

Max Activating Token Index: 432

Text #1

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4808. Min Act: -0.0000

Data Index: 615100 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4023. Min Act: -0.0000

Data Index: 886525 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4514. Min Act: -0.0000

Data Index: 797558 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3949. Min Act: -0.0000

Data Index: 316566 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4075. Min Act: -0.0000

Data Index: 1086679 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4015. Min Act: -0.0000

Data Index: 715843 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3773. Min Act: -0.0000

Data Index: 632650 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3593. Min Act: -0.0000

Data Index: 371445 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3794. Min Act: -0.0000

Data Index: 582638 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3859. Min Act: -0.0000

Data Index: 1206602 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1656294 (Python Code)

Max Activating Token Index: 822

Text #12

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3407. Min Act: -0.0000

Data Index: 792473 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3626. Min Act: -0.0000

Data Index: 568551 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3554. Min Act: -0.0000

Data Index: 1139801 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3034. Min Act: -0.0000

Data Index: 1425522 (Python Code)

Max Activating Token Index: 707

Text #16

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1057044 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1568673 (Python Code)

Max Activating Token Index: 335

Text #18

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3501. Min Act: -0.0000

Data Index: 1368763 (Python Code)

Max Activating Token Index: 387

Text #19

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3474. Min Act: -0.0000

Data Index: 1397803 (Python Code)

Max Activating Token Index: 71