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

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

Neuron 2813 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4085. Min Range: -2.4085

Max Act: 2.4085. Min Act: -0.0000

Data Index: 249898 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 2.4085. Min Range: -2.4085

Max Act: 2.1129. Min Act: -0.0000

Data Index: 166600 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 2.4085. Min Range: -2.4085

Max Act: 1.9738. Min Act: -0.0000

Data Index: 173794 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 2.4085. Min Range: -2.4085

Max Act: 2.1015. Min Act: -0.0000

Data Index: 625410 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 2.4085. Min Range: -2.4085

Max Act: 2.0266. Min Act: -0.0000

Data Index: 1040607 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 2.4085. Min Range: -2.4085

Max Act: 1.9114. Min Act: -0.0000

Data Index: 867093 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 2.4085. Min Range: -2.4085

Max Act: 2.0771. Min Act: -0.0000

Data Index: 1272828 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 2.4085. Min Range: -2.4085

Max Act: 2.0873. Min Act: -0.0000

Data Index: 12462 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 2.4085. Min Range: -2.4085

Max Act: 2.1014. Min Act: -0.0000

Data Index: 1137494 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 2.4085. Min Range: -2.4085

Max Act: 1.8402. Min Act: -0.0000

Data Index: 534166 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 2.4085. Min Range: -2.4085

Max Act: 1.8163. Min Act: -0.0000

Data Index: 593263 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 2.4085. Min Range: -2.4085

Max Act: 1.8474. Min Act: -0.0000

Data Index: 1240294 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 2.4085. Min Range: -2.4085

Max Act: 1.8885. Min Act: -0.0000

Data Index: 74700 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 2.4085. Min Range: -2.4085

Max Act: 1.8041. Min Act: -0.0000

Data Index: 206299 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 2.4085. Min Range: -2.4085

Max Act: 1.8038. Min Act: -0.0000

Data Index: 868180 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 2.4085. Min Range: -2.4085

Max Act: 1.8660. Min Act: -0.0000

Data Index: 1187363 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 2.4085. Min Range: -2.4085

Max Act: 1.9521. Min Act: -0.0000

Data Index: 955284 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 2.4085. Min Range: -2.4085

Max Act: 1.8538. Min Act: -0.0000

Data Index: 1050064 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 2.4085. Min Range: -2.4085

Max Act: 1.8385. Min Act: -0.0000

Data Index: 657290 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 2.4085. Min Range: -2.4085

Max Act: 1.7268. Min Act: -0.0000

Data Index: 1319354 (C4 (Web Text))

Max Activating Token Index: 380