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

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

Neuron 482 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.8624. Min Act: -0.0000

Data Index: 1546109 (Python Code)

Max Activating Token Index: 665

Text #1

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.8160. Min Act: -0.0000

Data Index: 1599545 (Python Code)

Max Activating Token Index: 989

Text #2

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.7137. Min Act: -0.0000

Data Index: 1558121 (Python Code)

Max Activating Token Index: 277

Text #3

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.8861. Min Act: -0.0000

Data Index: 1453131 (Python Code)

Max Activating Token Index: 719

Text #4

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.6289. Min Act: -0.0000

Data Index: 1458425 (Python Code)

Max Activating Token Index: 585

Text #5

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.7280. Min Act: -0.0000

Data Index: 1487327 (Python Code)

Max Activating Token Index: 724

Text #6

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.4730. Min Act: -0.0000

Data Index: 1469060 (Python Code)

Max Activating Token Index: 722

Text #7

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.4581. Min Act: -0.0000

Data Index: 1647989 (Python Code)

Max Activating Token Index: 572

Text #8

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.5386. Min Act: -0.0000

Data Index: 1588332 (Python Code)

Max Activating Token Index: 137

Text #9

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.6020. Min Act: -0.0000

Data Index: 1625371 (Python Code)

Max Activating Token Index: 388

Text #10

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.4960. Min Act: -0.0000

Data Index: 1536712 (Python Code)

Max Activating Token Index: 213

Text #11

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.3041. Min Act: -0.0000

Data Index: 1484403 (Python Code)

Max Activating Token Index: 800

Text #12

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.5241. Min Act: -0.0000

Data Index: 1559617 (Python Code)

Max Activating Token Index: 811

Text #13

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.4336. Min Act: -0.0000

Data Index: 1513494 (Python Code)

Max Activating Token Index: 895

Text #14

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.3536. Min Act: -0.0000

Data Index: 1396992 (Python Code)

Max Activating Token Index: 332

Text #15

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.4324. Min Act: -0.0000

Data Index: 1526653 (Python Code)

Max Activating Token Index: 117

Text #16

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.4271. Min Act: -0.0000

Data Index: 1567582 (Python Code)

Max Activating Token Index: 160

Text #17

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.3466. Min Act: -0.0000

Data Index: 1529252 (Python Code)

Max Activating Token Index: 109

Text #18

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.3545. Min Act: -0.0000

Data Index: 1545972 (Python Code)

Max Activating Token Index: 207

Text #19

Max Range: 1.8861. Min Range: -1.8861

Max Act: 1.4089. Min Act: -0.0000

Data Index: 1563578 (Python Code)

Max Activating Token Index: 147