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

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

Neuron 1506 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: 2.9570. Min Range: -2.9570

Max Act: 2.9570. Min Act: -0.1700

Data Index: 657497 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 2.9570. Min Range: -2.9570

Max Act: 2.9431. Min Act: -0.1700

Data Index: 262363 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 2.9570. Min Range: -2.9570

Max Act: 2.9312. Min Act: -0.1700

Data Index: 993298 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 2.9570. Min Range: -2.9570

Max Act: 2.8810. Min Act: -0.1700

Data Index: 557671 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 2.9570. Min Range: -2.9570

Max Act: 2.8812. Min Act: -0.1700

Data Index: 191015 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 2.9570. Min Range: -2.9570

Max Act: 2.8499. Min Act: -0.1700

Data Index: 87133 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 2.9570. Min Range: -2.9570

Max Act: 2.8539. Min Act: -0.1700

Data Index: 232051 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 2.9570. Min Range: -2.9570

Max Act: 2.8482. Min Act: -0.1700

Data Index: 477071 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 2.9570. Min Range: -2.9570

Max Act: 2.8387. Min Act: -0.1700

Data Index: 1556538 (Python Code)

Max Activating Token Index: 61

Text #9

Max Range: 2.9570. Min Range: -2.9570

Max Act: 2.8300. Min Act: -0.1700

Data Index: 321399 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 2.9570. Min Range: -2.9570

Max Act: 2.8267. Min Act: -0.1700

Data Index: 93467 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 2.9570. Min Range: -2.9570

Max Act: 2.8276. Min Act: -0.1700

Data Index: 829904 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 2.9570. Min Range: -2.9570

Max Act: 2.8144. Min Act: -0.1700

Data Index: 1221923 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 2.9570. Min Range: -2.9570

Max Act: 2.8054. Min Act: -0.1700

Data Index: 880492 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 2.9570. Min Range: -2.9570

Max Act: 2.8158. Min Act: -0.1700

Data Index: 976362 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 2.9570. Min Range: -2.9570

Max Act: 2.8353. Min Act: -0.1700

Data Index: 994611 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 2.9570. Min Range: -2.9570

Max Act: 2.7991. Min Act: -0.1700

Data Index: 1425290 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 2.9570. Min Range: -2.9570

Max Act: 2.8012. Min Act: -0.1700

Data Index: 1624365 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 2.9570. Min Range: -2.9570

Max Act: 2.8026. Min Act: -0.1700

Data Index: 176470 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 2.9570. Min Range: -2.9570

Max Act: 2.7667. Min Act: -0.1700

Data Index: 944777 (C4 (Web Text))

Max Activating Token Index: 245