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

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

Neuron 2987 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: 1.3888. Min Range: -1.3888

Max Act: 1.3888. Min Act: -0.0000

Data Index: 1598441 (Python Code)

Max Activating Token Index: 760

Text #1

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.3806. Min Act: -0.0000

Data Index: 1527887 (Python Code)

Max Activating Token Index: 149

Text #2

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.2572. Min Act: -0.0000

Data Index: 1583109 (Python Code)

Max Activating Token Index: 166

Text #3

Max Range: 1.3888. Min Range: -1.3888

Max Act: 1.1177. Min Act: -0.0000

Data Index: 1503648 (Python Code)

Max Activating Token Index: 408

Text #4

Max Range: 1.3888. Min Range: -1.3888

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1477793 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 1.3888. Min Range: -1.3888

Max Act: 0.8993. Min Act: -0.0000

Data Index: 1534806 (Python Code)

Max Activating Token Index: 788

Text #6

Max Range: 1.3888. Min Range: -1.3888

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1590996 (Python Code)

Max Activating Token Index: 992

Text #7

Max Range: 1.3888. Min Range: -1.3888

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1518695 (Python Code)

Max Activating Token Index: 138

Text #8

Max Range: 1.3888. Min Range: -1.3888

Max Act: 0.8888. Min Act: -0.0000

Data Index: 1373472 (Python Code)

Max Activating Token Index: 792

Text #9

Max Range: 1.3888. Min Range: -1.3888

Max Act: 0.8267. Min Act: -0.0000

Data Index: 1457292 (Python Code)

Max Activating Token Index: 49

Text #10

Max Range: 1.3888. Min Range: -1.3888

Max Act: 0.8310. Min Act: -0.0000

Data Index: 1531058 (Python Code)

Max Activating Token Index: 128

Text #11

Max Range: 1.3888. Min Range: -1.3888

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1449171 (Python Code)

Max Activating Token Index: 265

Text #12

Max Range: 1.3888. Min Range: -1.3888

Max Act: 0.9093. Min Act: -0.0000

Data Index: 1536620 (Python Code)

Max Activating Token Index: 103

Text #13

Max Range: 1.3888. Min Range: -1.3888

Max Act: 0.8402. Min Act: -0.0000

Data Index: 1531028 (Python Code)

Max Activating Token Index: 767

Text #14

Max Range: 1.3888. Min Range: -1.3888

Max Act: 0.7844. Min Act: -0.0000

Data Index: 1402051 (Python Code)

Max Activating Token Index: 340

Text #15

Max Range: 1.3888. Min Range: -1.3888

Max Act: 0.7702. Min Act: -0.0000

Data Index: 1631188 (Python Code)

Max Activating Token Index: 188

Text #16

Max Range: 1.3888. Min Range: -1.3888

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1613825 (Python Code)

Max Activating Token Index: 72

Text #17

Max Range: 1.3888. Min Range: -1.3888

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1616477 (Python Code)

Max Activating Token Index: 505

Text #18

Max Range: 1.3888. Min Range: -1.3888

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1599938 (Python Code)

Max Activating Token Index: 472

Text #19

Max Range: 1.3888. Min Range: -1.3888

Max Act: 0.7052. Min Act: -0.0000

Data Index: 1507541 (Python Code)

Max Activating Token Index: 847