Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1525 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2632. Min Act: -0.0003

Data Index: 1254953 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2547. Min Act: -0.0004

Data Index: 521938 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2577. Min Act: -0.0003

Data Index: 231454 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2564. Min Act: -0.0003

Data Index: 1558329 (Python Code)

Max Activating Token Index: 806

Text #4

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2461. Min Act: -0.0003

Data Index: 804553 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2542. Min Act: -0.0003

Data Index: 1637340 (Python Code)

Max Activating Token Index: 339

Text #6

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2365. Min Act: -0.0003

Data Index: 1055736 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2340. Min Act: -0.0003

Data Index: 437022 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2276. Min Act: -0.0003

Data Index: 1248792 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2335. Min Act: -0.0003

Data Index: 621280 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2263. Min Act: -0.0003

Data Index: 1052608 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2230. Min Act: -0.0003

Data Index: 1183058 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2201. Min Act: -0.0003

Data Index: 587245 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2138. Min Act: -0.0003

Data Index: 1291595 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2194. Min Act: -0.0003

Data Index: 1531670 (Python Code)

Max Activating Token Index: 753

Text #15

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2121. Min Act: -0.0003

Data Index: 208498 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2149. Min Act: -0.0003

Data Index: 1215399 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2105. Min Act: -0.0003

Data Index: 1355036 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2096. Min Act: -0.0003

Data Index: 1441029 (Python Code)

Max Activating Token Index: 661

Text #19

Max Range: 0.2632. Min Range: -0.2632

Max Act: 0.2123. Min Act: -0.0003

Data Index: 298747 (C4 (Web Text))

Max Activating Token Index: 342