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

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

Neuron 148 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: 3.2711. Min Range: -3.2711

Max Act: 3.2711. Min Act: -0.1700

Data Index: 107782 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 3.2711. Min Range: -3.2711

Max Act: 3.2480. Min Act: -0.1700

Data Index: 191282 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 3.2711. Min Range: -3.2711

Max Act: 3.2065. Min Act: -0.1700

Data Index: 460713 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 3.2711. Min Range: -3.2711

Max Act: 3.2111. Min Act: -0.1700

Data Index: 319251 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 3.2711. Min Range: -3.2711

Max Act: 3.2046. Min Act: -0.1699

Data Index: 490161 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 3.2711. Min Range: -3.2711

Max Act: 3.1948. Min Act: -0.1700

Data Index: 1057888 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 3.2711. Min Range: -3.2711

Max Act: 3.1750. Min Act: -0.1700

Data Index: 1619241 (Python Code)

Max Activating Token Index: 50

Text #7

Max Range: 3.2711. Min Range: -3.2711

Max Act: 3.1602. Min Act: -0.1699

Data Index: 276395 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 3.2711. Min Range: -3.2711

Max Act: 3.1635. Min Act: -0.1700

Data Index: 1472016 (Python Code)

Max Activating Token Index: 593

Text #9

Max Range: 3.2711. Min Range: -3.2711

Max Act: 3.1632. Min Act: -0.1700

Data Index: 106785 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 3.2711. Min Range: -3.2711

Max Act: 3.1299. Min Act: -0.1700

Data Index: 168287 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 3.2711. Min Range: -3.2711

Max Act: 3.1301. Min Act: -0.1700

Data Index: 440291 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 3.2711. Min Range: -3.2711

Max Act: 3.1387. Min Act: -0.1700

Data Index: 1229556 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 3.2711. Min Range: -3.2711

Max Act: 3.1282. Min Act: -0.1700

Data Index: 1546138 (Python Code)

Max Activating Token Index: 32

Text #14

Max Range: 3.2711. Min Range: -3.2711

Max Act: 3.1171. Min Act: -0.1700

Data Index: 333055 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 3.2711. Min Range: -3.2711

Max Act: 3.1218. Min Act: -0.1700

Data Index: 537456 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 3.2711. Min Range: -3.2711

Max Act: 3.1175. Min Act: -0.1700

Data Index: 259081 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 3.2711. Min Range: -3.2711

Max Act: 3.1077. Min Act: -0.1700

Data Index: 1487576 (Python Code)

Max Activating Token Index: 404

Text #18

Max Range: 3.2711. Min Range: -3.2711

Max Act: 3.1030. Min Act: -0.1700

Data Index: 455465 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 3.2711. Min Range: -3.2711

Max Act: 3.1017. Min Act: -0.1700

Data Index: 858569 (C4 (Web Text))

Max Activating Token Index: 503