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

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

Neuron 1566 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: 3.3688. Min Range: -3.3688

Max Act: 3.3688. Min Act: -0.1700

Data Index: 1607051 (Python Code)

Max Activating Token Index: 967

Text #1

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.3620. Min Act: -0.1700

Data Index: 127009 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.3517. Min Act: -0.1699

Data Index: 1374626 (Python Code)

Max Activating Token Index: 399

Text #3

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.3565. Min Act: -0.1700

Data Index: 1443583 (Python Code)

Max Activating Token Index: 60

Text #4

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.3391. Min Act: -0.1700

Data Index: 1587852 (Python Code)

Max Activating Token Index: 813

Text #5

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.3241. Min Act: -0.1700

Data Index: 1525716 (Python Code)

Max Activating Token Index: 229

Text #6

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.3222. Min Act: -0.1700

Data Index: 1613258 (Python Code)

Max Activating Token Index: 288

Text #7

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.2643. Min Act: -0.1700

Data Index: 1539405 (Python Code)

Max Activating Token Index: 198

Text #8

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.2524. Min Act: -0.1700

Data Index: 1236974 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.2657. Min Act: -0.1700

Data Index: 1637680 (Python Code)

Max Activating Token Index: 596

Text #10

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.2665. Min Act: -0.1700

Data Index: 1611122 (Python Code)

Max Activating Token Index: 309

Text #11

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.2785. Min Act: -0.1700

Data Index: 1586839 (Python Code)

Max Activating Token Index: 990

Text #12

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.2576. Min Act: -0.1700

Data Index: 1446112 (Python Code)

Max Activating Token Index: 59

Text #13

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.2667. Min Act: -0.1699

Data Index: 1557784 (Python Code)

Max Activating Token Index: 70

Text #14

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.2512. Min Act: -0.1700

Data Index: 1539222 (Python Code)

Max Activating Token Index: 155

Text #15

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.2511. Min Act: -0.1699

Data Index: 1569505 (Python Code)

Max Activating Token Index: 388

Text #16

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.2528. Min Act: -0.1700

Data Index: 1617070 (Python Code)

Max Activating Token Index: 181

Text #17

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.2612. Min Act: -0.1700

Data Index: 1631353 (Python Code)

Max Activating Token Index: 331

Text #18

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.2436. Min Act: -0.1700

Data Index: 1181291 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.2265. Min Act: -0.1700

Data Index: 41996 (C4 (Web Text))

Max Activating Token Index: 361