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

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

Neuron 1352 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: 4.0153. Min Range: -4.0153

Max Act: 4.0153. Min Act: -0.1700

Data Index: 386538 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.9980. Min Act: -0.1700

Data Index: 973185 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.9090. Min Act: -0.1700

Data Index: 1373205 (Python Code)

Max Activating Token Index: 907

Text #3

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.9230. Min Act: -0.1700

Data Index: 1568234 (Python Code)

Max Activating Token Index: 652

Text #4

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.9400. Min Act: -0.1700

Data Index: 866678 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.8894. Min Act: -0.1700

Data Index: 393358 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.8994. Min Act: -0.1700

Data Index: 1414385 (Python Code)

Max Activating Token Index: 69

Text #7

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.8758. Min Act: -0.1700

Data Index: 1107631 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.8922. Min Act: -0.1700

Data Index: 1212718 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.8832. Min Act: -0.1700

Data Index: 601959 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.8891. Min Act: -0.1700

Data Index: 612121 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.8819. Min Act: -0.1700

Data Index: 1608101 (Python Code)

Max Activating Token Index: 38

Text #12

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.8862. Min Act: -0.1700

Data Index: 1644298 (Python Code)

Max Activating Token Index: 133

Text #13

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.8677. Min Act: -0.1700

Data Index: 1406951 (Python Code)

Max Activating Token Index: 535

Text #14

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.8770. Min Act: -0.1700

Data Index: 1069220 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.8505. Min Act: -0.1700

Data Index: 531163 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.8467. Min Act: -0.1700

Data Index: 1590654 (Python Code)

Max Activating Token Index: 357

Text #17

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.8280. Min Act: -0.1700

Data Index: 1620789 (Python Code)

Max Activating Token Index: 40

Text #18

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.8328. Min Act: -0.1700

Data Index: 19698 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 4.0153. Min Range: -4.0153

Max Act: 3.8476. Min Act: -0.1700

Data Index: 4245 (C4 (Web Text))

Max Activating Token Index: 56