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

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

Neuron 396 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: 2.1198. Min Range: -2.1198

Max Act: 2.1198. Min Act: -0.0000

Data Index: 1570438 (Python Code)

Max Activating Token Index: 479

Text #1

Max Range: 2.1198. Min Range: -2.1198

Max Act: 2.0121. Min Act: -0.0000

Data Index: 727080 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 2.1198. Min Range: -2.1198

Max Act: 1.8945. Min Act: -0.0000

Data Index: 1378984 (Python Code)

Max Activating Token Index: 39

Text #3

Max Range: 2.1198. Min Range: -2.1198

Max Act: 1.7907. Min Act: -0.0000

Data Index: 1403623 (Python Code)

Max Activating Token Index: 430

Text #4

Max Range: 2.1198. Min Range: -2.1198

Max Act: 1.9694. Min Act: -0.0000

Data Index: 630097 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 2.1198. Min Range: -2.1198

Max Act: 1.8884. Min Act: -0.0000

Data Index: 352983 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 2.1198. Min Range: -2.1198

Max Act: 1.7722. Min Act: -0.0000

Data Index: 1197014 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 2.1198. Min Range: -2.1198

Max Act: 1.7481. Min Act: -0.0000

Data Index: 399396 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 2.1198. Min Range: -2.1198

Max Act: 1.7174. Min Act: -0.0000

Data Index: 1499877 (Python Code)

Max Activating Token Index: 575

Text #9

Max Range: 2.1198. Min Range: -2.1198

Max Act: 1.7248. Min Act: -0.0000

Data Index: 1367666 (Python Code)

Max Activating Token Index: 338

Text #10

Max Range: 2.1198. Min Range: -2.1198

Max Act: 1.6131. Min Act: -0.0000

Data Index: 854123 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 2.1198. Min Range: -2.1198

Max Act: 1.5895. Min Act: -0.0000

Data Index: 1649996 (Python Code)

Max Activating Token Index: 211

Text #12

Max Range: 2.1198. Min Range: -2.1198

Max Act: 1.4864. Min Act: -0.0000

Data Index: 1322226 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 2.1198. Min Range: -2.1198

Max Act: 1.4962. Min Act: -0.0000

Data Index: 1505600 (Python Code)

Max Activating Token Index: 163

Text #14

Max Range: 2.1198. Min Range: -2.1198

Max Act: 1.4847. Min Act: -0.0000

Data Index: 1551931 (Python Code)

Max Activating Token Index: 869

Text #15

Max Range: 2.1198. Min Range: -2.1198

Max Act: 1.6634. Min Act: -0.0000

Data Index: 1606156 (Python Code)

Max Activating Token Index: 643

Text #16

Max Range: 2.1198. Min Range: -2.1198

Max Act: 1.5592. Min Act: -0.0000

Data Index: 841620 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 2.1198. Min Range: -2.1198

Max Act: 1.6442. Min Act: -0.0000

Data Index: 1257744 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 2.1198. Min Range: -2.1198

Max Act: 1.5293. Min Act: -0.0000

Data Index: 193898 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 2.1198. Min Range: -2.1198

Max Act: 1.5062. Min Act: -0.0000

Data Index: 586990 (C4 (Web Text))

Max Activating Token Index: 532