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

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

Neuron 1602 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.7313. Min Act: -0.0000

Data Index: 1427509 (Python Code)

Max Activating Token Index: 218

Text #1

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.8721. Min Act: -0.0000

Data Index: 1517930 (Python Code)

Max Activating Token Index: 631

Text #2

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.6901. Min Act: -0.0000

Data Index: 1504106 (Python Code)

Max Activating Token Index: 340

Text #3

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.7907. Min Act: -0.0000

Data Index: 1647002 (Python Code)

Max Activating Token Index: 497

Text #4

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.9062. Min Act: -0.0000

Data Index: 1531415 (Python Code)

Max Activating Token Index: 345

Text #5

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.7275. Min Act: -0.0000

Data Index: 1611192 (Python Code)

Max Activating Token Index: 685

Text #6

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.8565. Min Act: -0.0000

Data Index: 1492499 (Python Code)

Max Activating Token Index: 1004

Text #7

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.7073. Min Act: -0.0000

Data Index: 1566909 (Python Code)

Max Activating Token Index: 546

Text #8

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.5139. Min Act: -0.0000

Data Index: 1501936 (Python Code)

Max Activating Token Index: 938

Text #9

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.6369. Min Act: -0.0000

Data Index: 1517446 (Python Code)

Max Activating Token Index: 515

Text #10

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.6498. Min Act: -0.0000

Data Index: 1386788 (Python Code)

Max Activating Token Index: 534

Text #11

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.4976. Min Act: -0.0000

Data Index: 1581196 (Python Code)

Max Activating Token Index: 535

Text #12

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.7320. Min Act: -0.0000

Data Index: 1394592 (Python Code)

Max Activating Token Index: 153

Text #13

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.5305. Min Act: -0.0000

Data Index: 1439680 (Python Code)

Max Activating Token Index: 548

Text #14

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.5020. Min Act: -0.0000

Data Index: 1591511 (Python Code)

Max Activating Token Index: 899

Text #15

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.2449. Min Act: -0.0000

Data Index: 1532891 (Python Code)

Max Activating Token Index: 759

Text #16

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.6016. Min Act: -0.0000

Data Index: 1553329 (Python Code)

Max Activating Token Index: 775

Text #17

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.7049. Min Act: -0.0000

Data Index: 1443716 (Python Code)

Max Activating Token Index: 196

Text #18

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.4371. Min Act: -0.0000

Data Index: 1402336 (Python Code)

Max Activating Token Index: 96

Text #19

Max Range: 2.9062. Min Range: -2.9062

Max Act: 2.4251. Min Act: -0.0000

Data Index: 1455857 (Python Code)

Max Activating Token Index: 485