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

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

Neuron 2824 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0428. Min Range: -1.0428

Max Act: 1.0232. Min Act: -0.0000

Data Index: 1287908 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.9530. Min Act: -0.0000

Data Index: 327322 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.9549. Min Act: -0.0000

Data Index: 38833 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1306264 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 1.0428. Min Range: -1.0428

Max Act: 1.0428. Min Act: -0.0000

Data Index: 365777 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.9120. Min Act: -0.0000

Data Index: 293959 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.8892. Min Act: -0.0000

Data Index: 711311 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.8936. Min Act: -0.0000

Data Index: 996011 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.8282. Min Act: -0.0000

Data Index: 917038 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7823. Min Act: -0.0000

Data Index: 478749 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.8181. Min Act: -0.0000

Data Index: 1273938 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7343. Min Act: -0.0000

Data Index: 421219 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7823. Min Act: -0.0000

Data Index: 442866 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7945. Min Act: -0.0000

Data Index: 679526 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7683. Min Act: -0.0000

Data Index: 1001817 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7880. Min Act: -0.0000

Data Index: 423296 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1254490 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1215296 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7220. Min Act: -0.0000

Data Index: 405760 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.6980. Min Act: -0.0000

Data Index: 608083 (C4 (Web Text))

Max Activating Token Index: 288