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

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

Neuron 5935 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.3069. Min Act: -0.0001

Data Index: 76694 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2860. Min Act: -0.0001

Data Index: 62604 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2725. Min Act: -0.0001

Data Index: 577668 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2473. Min Act: -0.0001

Data Index: 1318786 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2624. Min Act: -0.0001

Data Index: 280133 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2478. Min Act: -0.0001

Data Index: 516496 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2603. Min Act: -0.0001

Data Index: 903824 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2430. Min Act: -0.0001

Data Index: 1937 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2564. Min Act: -0.0001

Data Index: 36307 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2402. Min Act: -0.0001

Data Index: 716960 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2533. Min Act: -0.0001

Data Index: 1116287 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2310. Min Act: -0.0001

Data Index: 644789 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2164. Min Act: -0.0001

Data Index: 1280783 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2278. Min Act: -0.0001

Data Index: 132341 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2268. Min Act: -0.0001

Data Index: 815184 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2227. Min Act: -0.0001

Data Index: 999276 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2049. Min Act: -0.0001

Data Index: 1279296 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2206. Min Act: -0.0001

Data Index: 1074751 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2249. Min Act: -0.0001

Data Index: 224328 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2137. Min Act: -0.0001

Data Index: 692850 (C4 (Web Text))

Max Activating Token Index: 352