Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 68 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.6769. Min Act: -0.1700

Data Index: 3204617 (Open Web Text)

Max Activating Token Index: 502

Text #1

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.6080. Min Act: -0.1700

Data Index: 962889 (Open Web Text)

Max Activating Token Index: 288

Text #2

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.5840. Min Act: -0.1700

Data Index: 1445352 (Open Web Text)

Max Activating Token Index: 591

Text #3

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.5536. Min Act: -0.1700

Data Index: 8765202 (Open Web Text)

Max Activating Token Index: 592

Text #4

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.5534. Min Act: -0.1700

Data Index: 708138 (Open Web Text)

Max Activating Token Index: 455

Text #5

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.5666. Min Act: -0.1700

Data Index: 3778142 (Open Web Text)

Max Activating Token Index: 242

Text #6

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.5209. Min Act: -0.1700

Data Index: 3930351 (Open Web Text)

Max Activating Token Index: 477

Text #7

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.5276. Min Act: -0.1700

Data Index: 3357878 (Open Web Text)

Max Activating Token Index: 277

Text #8

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.4942. Min Act: -0.1700

Data Index: 3871561 (Open Web Text)

Max Activating Token Index: 472

Text #9

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.4902. Min Act: -0.1700

Data Index: 6372237 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.4847. Min Act: -0.1700

Data Index: 840827 (Open Web Text)

Max Activating Token Index: 1009

Text #11

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.4588. Min Act: -0.1700

Data Index: 1887234 (Open Web Text)

Max Activating Token Index: 869

Text #12

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.4496. Min Act: -0.1700

Data Index: 2390815 (Open Web Text)

Max Activating Token Index: 844

Text #13

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.4496. Min Act: -0.1700

Data Index: 157792 (Open Web Text)

Max Activating Token Index: 593

Text #14

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.4540. Min Act: -0.1700

Data Index: 7419012 (Open Web Text)

Max Activating Token Index: 848

Text #15

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.4497. Min Act: -0.1700

Data Index: 2402966 (Open Web Text)

Max Activating Token Index: 731

Text #16

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.4655. Min Act: -0.1700

Data Index: 382061 (Open Web Text)

Max Activating Token Index: 521

Text #17

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.4586. Min Act: -0.1700

Data Index: 4836707 (Open Web Text)

Max Activating Token Index: 376

Text #18

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.4330. Min Act: -0.1700

Data Index: 2598563 (Open Web Text)

Max Activating Token Index: 24

Text #19

Max Range: 3.6769. Min Range: -3.6769

Max Act: 3.4397. Min Act: -0.1700

Data Index: 6992794 (Open Web Text)

Max Activating Token Index: 162