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

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

Neuron 632 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: 3.1632. Min Range: -3.1632

Max Act: 3.1632. Min Act: -0.1700

Data Index: 1395880 (Python Code)

Max Activating Token Index: 170

Text #1

Max Range: 3.1632. Min Range: -3.1632

Max Act: 3.1409. Min Act: -0.1700

Data Index: 1402222 (Python Code)

Max Activating Token Index: 937

Text #2

Max Range: 3.1632. Min Range: -3.1632

Max Act: 3.1250. Min Act: -0.1700

Data Index: 1626520 (Python Code)

Max Activating Token Index: 843

Text #3

Max Range: 3.1632. Min Range: -3.1632

Max Act: 3.0948. Min Act: -0.1700

Data Index: 1561932 (Python Code)

Max Activating Token Index: 765

Text #4

Max Range: 3.1632. Min Range: -3.1632

Max Act: 3.0968. Min Act: -0.1700

Data Index: 1541875 (Python Code)

Max Activating Token Index: 774

Text #5

Max Range: 3.1632. Min Range: -3.1632

Max Act: 3.0642. Min Act: -0.1700

Data Index: 1623549 (Python Code)

Max Activating Token Index: 990

Text #6

Max Range: 3.1632. Min Range: -3.1632

Max Act: 3.0253. Min Act: -0.1700

Data Index: 1378196 (Python Code)

Max Activating Token Index: 566

Text #7

Max Range: 3.1632. Min Range: -3.1632

Max Act: 3.0300. Min Act: -0.1700

Data Index: 1644307 (Python Code)

Max Activating Token Index: 661

Text #8

Max Range: 3.1632. Min Range: -3.1632

Max Act: 3.0042. Min Act: -0.1700

Data Index: 1418508 (Python Code)

Max Activating Token Index: 941

Text #9

Max Range: 3.1632. Min Range: -3.1632

Max Act: 2.9770. Min Act: -0.1700

Data Index: 1543168 (Python Code)

Max Activating Token Index: 478

Text #10

Max Range: 3.1632. Min Range: -3.1632

Max Act: 2.9760. Min Act: -0.1700

Data Index: 1553247 (Python Code)

Max Activating Token Index: 254

Text #11

Max Range: 3.1632. Min Range: -3.1632

Max Act: 2.9742. Min Act: -0.1700

Data Index: 1428687 (Python Code)

Max Activating Token Index: 567

Text #12

Max Range: 3.1632. Min Range: -3.1632

Max Act: 3.0015. Min Act: -0.1700

Data Index: 1381503 (Python Code)

Max Activating Token Index: 996

Text #13

Max Range: 3.1632. Min Range: -3.1632

Max Act: 2.9652. Min Act: -0.1700

Data Index: 1366441 (Python Code)

Max Activating Token Index: 716

Text #14

Max Range: 3.1632. Min Range: -3.1632

Max Act: 2.9600. Min Act: -0.1700

Data Index: 1351876 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 3.1632. Min Range: -3.1632

Max Act: 2.9480. Min Act: -0.1700

Data Index: 7081 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 3.1632. Min Range: -3.1632

Max Act: 2.9498. Min Act: -0.1700

Data Index: 1474195 (Python Code)

Max Activating Token Index: 108

Text #17

Max Range: 3.1632. Min Range: -3.1632

Max Act: 2.9386. Min Act: -0.1700

Data Index: 1400605 (Python Code)

Max Activating Token Index: 463

Text #18

Max Range: 3.1632. Min Range: -3.1632

Max Act: 2.9115. Min Act: -0.1700

Data Index: 1486645 (Python Code)

Max Activating Token Index: 975

Text #19

Max Range: 3.1632. Min Range: -3.1632

Max Act: 2.9080. Min Act: -0.1700

Data Index: 395858 (C4 (Web Text))

Max Activating Token Index: 66