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

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

Neuron 874 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: 4.4547. Min Range: -4.4547

Max Act: 4.4338. Min Act: -0.1699

Data Index: 1547275 (Python Code)

Max Activating Token Index: 286

Text #1

Max Range: 4.4547. Min Range: -4.4547

Max Act: 4.4479. Min Act: -0.1700

Data Index: 1381362 (Python Code)

Max Activating Token Index: 856

Text #2

Max Range: 4.4547. Min Range: -4.4547

Max Act: 4.4547. Min Act: -0.1700

Data Index: 1557525 (Python Code)

Max Activating Token Index: 678

Text #3

Max Range: 4.4547. Min Range: -4.4547

Max Act: 4.3718. Min Act: -0.1700

Data Index: 1618613 (Python Code)

Max Activating Token Index: 137

Text #4

Max Range: 4.4547. Min Range: -4.4547

Max Act: 4.3830. Min Act: -0.1700

Data Index: 1498391 (Python Code)

Max Activating Token Index: 129

Text #5

Max Range: 4.4547. Min Range: -4.4547

Max Act: 4.3904. Min Act: -0.1698

Data Index: 1360837 (Python Code)

Max Activating Token Index: 500

Text #6

Max Range: 4.4547. Min Range: -4.4547

Max Act: 4.3222. Min Act: -0.1699

Data Index: 1422271 (Python Code)

Max Activating Token Index: 671

Text #7

Max Range: 4.4547. Min Range: -4.4547

Max Act: 4.3722. Min Act: -0.1700

Data Index: 1445213 (Python Code)

Max Activating Token Index: 303

Text #8

Max Range: 4.4547. Min Range: -4.4547

Max Act: 4.2972. Min Act: -0.1700

Data Index: 1643366 (Python Code)

Max Activating Token Index: 903

Text #9

Max Range: 4.4547. Min Range: -4.4547

Max Act: 4.3176. Min Act: -0.1700

Data Index: 1498832 (Python Code)

Max Activating Token Index: 841

Text #10

Max Range: 4.4547. Min Range: -4.4547

Max Act: 4.2716. Min Act: -0.1700

Data Index: 1364968 (Python Code)

Max Activating Token Index: 859

Text #11

Max Range: 4.4547. Min Range: -4.4547

Max Act: 4.2869. Min Act: -0.1698

Data Index: 1568491 (Python Code)

Max Activating Token Index: 228

Text #12

Max Range: 4.4547. Min Range: -4.4547

Max Act: 4.2612. Min Act: -0.1700

Data Index: 1622486 (Python Code)

Max Activating Token Index: 283

Text #13

Max Range: 4.4547. Min Range: -4.4547

Max Act: 4.2491. Min Act: -0.1700

Data Index: 1569862 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 4.4547. Min Range: -4.4547

Max Act: 4.2686. Min Act: -0.1699

Data Index: 1395730 (Python Code)

Max Activating Token Index: 766

Text #15

Max Range: 4.4547. Min Range: -4.4547

Max Act: 4.2590. Min Act: -0.1700

Data Index: 1623839 (Python Code)

Max Activating Token Index: 8

Text #16

Max Range: 4.4547. Min Range: -4.4547

Max Act: 4.2318. Min Act: -0.1699

Data Index: 1513105 (Python Code)

Max Activating Token Index: 992

Text #17

Max Range: 4.4547. Min Range: -4.4547

Max Act: 4.2217. Min Act: -0.1693

Data Index: 1423759 (Python Code)

Max Activating Token Index: 715

Text #18

Max Range: 4.4547. Min Range: -4.4547

Max Act: 4.2195. Min Act: -0.1700

Data Index: 1398260 (Python Code)

Max Activating Token Index: 127

Text #19

Max Range: 4.4547. Min Range: -4.4547

Max Act: 4.2140. Min Act: -0.1700

Data Index: 1600369 (Python Code)

Max Activating Token Index: 551