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

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

Neuron 5296 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: 1.9685. Min Range: -1.9685

Max Act: 1.9685. Min Act: -0.0000

Data Index: 945319 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 1.9685. Min Range: -1.9685

Max Act: 1.7728. Min Act: -0.0000

Data Index: 528825 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 1.9685. Min Range: -1.9685

Max Act: 1.5009. Min Act: -0.0000

Data Index: 293196 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 1.9685. Min Range: -1.9685

Max Act: 1.4439. Min Act: -0.0000

Data Index: 46792 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 1.9685. Min Range: -1.9685

Max Act: 1.1309. Min Act: -0.0000

Data Index: 519883 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 1.9685. Min Range: -1.9685

Max Act: 1.1488. Min Act: -0.0000

Data Index: 527489 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 1.9685. Min Range: -1.9685

Max Act: 1.0437. Min Act: -0.0000

Data Index: 823694 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 1.9685. Min Range: -1.9685

Max Act: 0.9895. Min Act: -0.0000

Data Index: 818171 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 1.9685. Min Range: -1.9685

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1582322 (Python Code)

Max Activating Token Index: 750

Text #9

Max Range: 1.9685. Min Range: -1.9685

Max Act: 1.0688. Min Act: -0.0000

Data Index: 482760 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 1.9685. Min Range: -1.9685

Max Act: 1.0108. Min Act: -0.0000

Data Index: 1110589 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 1.9685. Min Range: -1.9685

Max Act: 1.0267. Min Act: -0.0000

Data Index: 1023893 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 1.9685. Min Range: -1.9685

Max Act: 1.0274. Min Act: -0.0000

Data Index: 1610133 (Python Code)

Max Activating Token Index: 275

Text #13

Max Range: 1.9685. Min Range: -1.9685

Max Act: 1.0150. Min Act: -0.0000

Data Index: 998410 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 1.9685. Min Range: -1.9685

Max Act: 0.9577. Min Act: -0.0000

Data Index: 1396108 (Python Code)

Max Activating Token Index: 94

Text #15

Max Range: 1.9685. Min Range: -1.9685

Max Act: 0.9330. Min Act: -0.0000

Data Index: 354015 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 1.9685. Min Range: -1.9685

Max Act: 0.9483. Min Act: -0.0000

Data Index: 948510 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 1.9685. Min Range: -1.9685

Max Act: 0.9206. Min Act: -0.0000

Data Index: 186595 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 1.9685. Min Range: -1.9685

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1546716 (Python Code)

Max Activating Token Index: 495

Text #19

Max Range: 1.9685. Min Range: -1.9685

Max Act: 0.9063. Min Act: -0.0000

Data Index: 1301927 (C4 (Web Text))

Max Activating Token Index: 82