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

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

Neuron 2604 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: 1.8931. Min Range: -1.8931

Max Act: 1.8633. Min Act: -0.0000

Data Index: 1404965 (Python Code)

Max Activating Token Index: 171

Text #1

Max Range: 1.8931. Min Range: -1.8931

Max Act: 1.8931. Min Act: -0.0000

Data Index: 1464175 (Python Code)

Max Activating Token Index: 360

Text #2

Max Range: 1.8931. Min Range: -1.8931

Max Act: 1.7503. Min Act: -0.0000

Data Index: 1544568 (Python Code)

Max Activating Token Index: 99

Text #3

Max Range: 1.8931. Min Range: -1.8931

Max Act: 1.7328. Min Act: -0.0000

Data Index: 1520209 (Python Code)

Max Activating Token Index: 504

Text #4

Max Range: 1.8931. Min Range: -1.8931

Max Act: 1.7148. Min Act: -0.0000

Data Index: 684004 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 1.8931. Min Range: -1.8931

Max Act: 1.6104. Min Act: -0.0000

Data Index: 1431553 (Python Code)

Max Activating Token Index: 114

Text #6

Max Range: 1.8931. Min Range: -1.8931

Max Act: 1.5730. Min Act: -0.0000

Data Index: 1484110 (Python Code)

Max Activating Token Index: 30

Text #7

Max Range: 1.8931. Min Range: -1.8931

Max Act: 1.3517. Min Act: -0.0000

Data Index: 1438370 (Python Code)

Max Activating Token Index: 793

Text #8

Max Range: 1.8931. Min Range: -1.8931

Max Act: 1.4565. Min Act: -0.0000

Data Index: 1467714 (Python Code)

Max Activating Token Index: 447

Text #9

Max Range: 1.8931. Min Range: -1.8931

Max Act: 1.3279. Min Act: -0.0000

Data Index: 1541405 (Python Code)

Max Activating Token Index: 812

Text #10

Max Range: 1.8931. Min Range: -1.8931

Max Act: 1.3935. Min Act: -0.0000

Data Index: 1415061 (Python Code)

Max Activating Token Index: 256

Text #11

Max Range: 1.8931. Min Range: -1.8931

Max Act: 1.3408. Min Act: -0.0000

Data Index: 1389302 (Python Code)

Max Activating Token Index: 142

Text #12

Max Range: 1.8931. Min Range: -1.8931

Max Act: 1.2987. Min Act: -0.0000

Data Index: 1435587 (Python Code)

Max Activating Token Index: 645

Text #13

Max Range: 1.8931. Min Range: -1.8931

Max Act: 1.3009. Min Act: -0.0000

Data Index: 1435801 (Python Code)

Max Activating Token Index: 349

Text #14

Max Range: 1.8931. Min Range: -1.8931

Max Act: 1.2869. Min Act: -0.0000

Data Index: 1609362 (Python Code)

Max Activating Token Index: 82

Text #15

Max Range: 1.8931. Min Range: -1.8931

Max Act: 1.1889. Min Act: -0.0000

Data Index: 1450159 (Python Code)

Max Activating Token Index: 846

Text #16

Max Range: 1.8931. Min Range: -1.8931

Max Act: 1.2772. Min Act: -0.0000

Data Index: 1540075 (Python Code)

Max Activating Token Index: 859

Text #17

Max Range: 1.8931. Min Range: -1.8931

Max Act: 1.2519. Min Act: -0.0000

Data Index: 1602212 (Python Code)

Max Activating Token Index: 400

Text #18

Max Range: 1.8931. Min Range: -1.8931

Max Act: 1.2381. Min Act: -0.0000

Data Index: 1573850 (Python Code)

Max Activating Token Index: 653

Text #19

Max Range: 1.8931. Min Range: -1.8931

Max Act: 1.2524. Min Act: -0.0000

Data Index: 1424675 (Python Code)

Max Activating Token Index: 148