Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 168 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.3052. Min Act: -0.1700

Data Index: 1352175 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.2531. Min Act: -0.1700

Data Index: 1199959 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.2365. Min Act: -0.1700

Data Index: 768056 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.2269. Min Act: -0.1700

Data Index: 81622 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.2296. Min Act: -0.1700

Data Index: 890472 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.2380. Min Act: -0.1700

Data Index: 659061 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.1891. Min Act: -0.1700

Data Index: 516499 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.1991. Min Act: -0.1700

Data Index: 1342099 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.1964. Min Act: -0.1699

Data Index: 973930 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.1753. Min Act: -0.1700

Data Index: 17869 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.1731. Min Act: -0.1700

Data Index: 1006765 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.1375. Min Act: -0.1699

Data Index: 1358264 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.1417. Min Act: -0.1700

Data Index: 331645 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.1333. Min Act: -0.1700

Data Index: 756620 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.1505. Min Act: -0.1700

Data Index: 240230 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.1286. Min Act: -0.1700

Data Index: 957146 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.1355. Min Act: -0.1700

Data Index: 743778 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.1445. Min Act: -0.1700

Data Index: 1114047 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.1349. Min Act: -0.1700

Data Index: 573502 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 3.3052. Min Range: -3.3052

Max Act: 3.1322. Min Act: -0.1700

Data Index: 441455 (C4 (Web Text))

Max Activating Token Index: 508