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

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

Neuron 626 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: 4.0426. Min Range: -4.0426

Max Act: 4.0426. Min Act: -0.1700

Data Index: 1400623 (Python Code)

Max Activating Token Index: 831

Text #1

Max Range: 4.0426. Min Range: -4.0426

Max Act: 3.9983. Min Act: -0.1700

Data Index: 1449286 (Python Code)

Max Activating Token Index: 550

Text #2

Max Range: 4.0426. Min Range: -4.0426

Max Act: 3.9926. Min Act: -0.1700

Data Index: 1397623 (Python Code)

Max Activating Token Index: 633

Text #3

Max Range: 4.0426. Min Range: -4.0426

Max Act: 3.9960. Min Act: -0.1700

Data Index: 1608233 (Python Code)

Max Activating Token Index: 224

Text #4

Max Range: 4.0426. Min Range: -4.0426

Max Act: 3.9874. Min Act: -0.1700

Data Index: 1363124 (Python Code)

Max Activating Token Index: 92

Text #5

Max Range: 4.0426. Min Range: -4.0426

Max Act: 3.9789. Min Act: -0.1700

Data Index: 1380895 (Python Code)

Max Activating Token Index: 969

Text #6

Max Range: 4.0426. Min Range: -4.0426

Max Act: 3.9168. Min Act: -0.1700

Data Index: 374239 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 4.0426. Min Range: -4.0426

Max Act: 3.9545. Min Act: -0.1700

Data Index: 1593410 (Python Code)

Max Activating Token Index: 15

Text #8

Max Range: 4.0426. Min Range: -4.0426

Max Act: 3.9100. Min Act: -0.1700

Data Index: 1655522 (Python Code)

Max Activating Token Index: 33

Text #9

Max Range: 4.0426. Min Range: -4.0426

Max Act: 3.9233. Min Act: -0.1700

Data Index: 285815 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 4.0426. Min Range: -4.0426

Max Act: 3.9535. Min Act: -0.1700

Data Index: 1468683 (Python Code)

Max Activating Token Index: 998

Text #11

Max Range: 4.0426. Min Range: -4.0426

Max Act: 3.8902. Min Act: -0.1700

Data Index: 1602747 (Python Code)

Max Activating Token Index: 19

Text #12

Max Range: 4.0426. Min Range: -4.0426

Max Act: 3.8771. Min Act: -0.1700

Data Index: 1366718 (Python Code)

Max Activating Token Index: 81

Text #13

Max Range: 4.0426. Min Range: -4.0426

Max Act: 3.8331. Min Act: -0.1700

Data Index: 1580000 (Python Code)

Max Activating Token Index: 868

Text #14

Max Range: 4.0426. Min Range: -4.0426

Max Act: 3.8281. Min Act: -0.1700

Data Index: 1637605 (Python Code)

Max Activating Token Index: 764

Text #15

Max Range: 4.0426. Min Range: -4.0426

Max Act: 3.8612. Min Act: -0.1700

Data Index: 1415019 (Python Code)

Max Activating Token Index: 795

Text #16

Max Range: 4.0426. Min Range: -4.0426

Max Act: 3.8386. Min Act: -0.1700

Data Index: 1370126 (Python Code)

Max Activating Token Index: 7

Text #17

Max Range: 4.0426. Min Range: -4.0426

Max Act: 3.8488. Min Act: -0.1700

Data Index: 1613850 (Python Code)

Max Activating Token Index: 589

Text #18

Max Range: 4.0426. Min Range: -4.0426

Max Act: 3.8116. Min Act: -0.1700

Data Index: 1555575 (Python Code)

Max Activating Token Index: 559

Text #19

Max Range: 4.0426. Min Range: -4.0426

Max Act: 3.8585. Min Act: -0.1700

Data Index: 1416778 (Python Code)

Max Activating Token Index: 833