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

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

Neuron 5033 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.2469. Min Range: -2.2469

Max Act: 2.2469. Min Act: -0.0002

Data Index: 754464 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 2.2469. Min Range: -2.2469

Max Act: 2.2403. Min Act: -0.0001

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 2.2469. Min Range: -2.2469

Max Act: 2.1352. Min Act: -0.0001

Data Index: 753996 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.8996. Min Act: -0.0001

Data Index: 1036914 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.8307. Min Act: -0.0002

Data Index: 689850 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.8221. Min Act: -0.0002

Data Index: 172178 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.8027. Min Act: -0.0002

Data Index: 549695 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.7312. Min Act: -0.0002

Data Index: 1469363 (Python Code)

Max Activating Token Index: 773

Text #8

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.7587. Min Act: -0.0001

Data Index: 613584 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.6975. Min Act: -0.0002

Data Index: 1139128 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.6577. Min Act: -0.0002

Data Index: 1134643 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.6626. Min Act: -0.0002

Data Index: 1336589 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.6725. Min Act: -0.0001

Data Index: 964755 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.5979. Min Act: -0.0002

Data Index: 53849 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.5668. Min Act: -0.0002

Data Index: 1632551 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.5644. Min Act: -0.0002

Data Index: 428009 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.5721. Min Act: -0.0002

Data Index: 1128049 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.5391. Min Act: -0.0002

Data Index: 432537 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.4949. Min Act: -0.0002

Data Index: 1462149 (Python Code)

Max Activating Token Index: 877

Text #19

Max Range: 2.2469. Min Range: -2.2469

Max Act: 1.5973. Min Act: -0.0002

Data Index: 210461 (C4 (Web Text))

Max Activating Token Index: 824