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

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

Neuron 4885 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: 3.1031. Min Range: -3.1031

Max Act: 3.1031. Min Act: -0.0000

Data Index: 1417230 (Python Code)

Max Activating Token Index: 154

Text #1

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.5955. Min Act: -0.0000

Data Index: 1602139 (Python Code)

Max Activating Token Index: 165

Text #2

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.5503. Min Act: -0.0000

Data Index: 1423608 (Python Code)

Max Activating Token Index: 800

Text #3

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.5996. Min Act: -0.0000

Data Index: 1570523 (Python Code)

Max Activating Token Index: 294

Text #4

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.6089. Min Act: 0.0000

Data Index: 1636540 (Python Code)

Max Activating Token Index: 73

Text #5

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.4960. Min Act: -0.0000

Data Index: 1516542 (Python Code)

Max Activating Token Index: 279

Text #6

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.5650. Min Act: -0.0000

Data Index: 1473542 (Python Code)

Max Activating Token Index: 17

Text #7

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.6772. Min Act: -0.0000

Data Index: 1629953 (Python Code)

Max Activating Token Index: 208

Text #8

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.6806. Min Act: -0.0000

Data Index: 1374451 (Python Code)

Max Activating Token Index: 224

Text #9

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.6920. Min Act: -0.0000

Data Index: 1453233 (Python Code)

Max Activating Token Index: 16

Text #10

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.3332. Min Act: 0.0000

Data Index: 1526735 (Python Code)

Max Activating Token Index: 323

Text #11

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.3409. Min Act: -0.0000

Data Index: 1545006 (Python Code)

Max Activating Token Index: 113

Text #12

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.3162. Min Act: 0.0000

Data Index: 1531881 (Python Code)

Max Activating Token Index: 217

Text #13

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.2767. Min Act: -0.0000

Data Index: 1463606 (Python Code)

Max Activating Token Index: 74

Text #14

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.1531. Min Act: -0.0000

Data Index: 1458475 (Python Code)

Max Activating Token Index: 915

Text #15

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.3669. Min Act: -0.0000

Data Index: 1558217 (Python Code)

Max Activating Token Index: 461

Text #16

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.2591. Min Act: -0.0000

Data Index: 1544049 (Python Code)

Max Activating Token Index: 345

Text #17

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.1135. Min Act: -0.0000

Data Index: 1470678 (Python Code)

Max Activating Token Index: 49

Text #18

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.1165. Min Act: -0.0000

Data Index: 1577128 (Python Code)

Max Activating Token Index: 236

Text #19

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.2023. Min Act: -0.0000

Data Index: 1576026 (Python Code)

Max Activating Token Index: 554