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

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

Neuron 2164 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: 1.3667. Min Range: -1.3667

Max Act: 1.3667. Min Act: -0.0002

Data Index: 19580 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.3062. Min Act: -0.0002

Data Index: 1263579 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.3094. Min Act: -0.0002

Data Index: 138673 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.3092. Min Act: -0.0002

Data Index: 1265470 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.3211. Min Act: -0.0002

Data Index: 1097450 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.3020. Min Act: -0.0002

Data Index: 1077502 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2845. Min Act: -0.0002

Data Index: 254516 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2659. Min Act: -0.0002

Data Index: 1054321 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2505. Min Act: -0.0002

Data Index: 267909 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2287. Min Act: -0.0003

Data Index: 207204 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2580. Min Act: -0.0002

Data Index: 1290191 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2416. Min Act: -0.0002

Data Index: 1091250 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2489. Min Act: -0.0002

Data Index: 25518 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2628. Min Act: -0.0003

Data Index: 1276873 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2507. Min Act: -0.0002

Data Index: 354301 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2218. Min Act: -0.0002

Data Index: 906842 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2231. Min Act: -0.0002

Data Index: 1089399 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2465. Min Act: -0.0002

Data Index: 49563 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2616. Min Act: -0.0002

Data Index: 706407 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2302. Min Act: -0.0002

Data Index: 30968 (C4 (Web Text))

Max Activating Token Index: 661