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

Dataset: Open Web Text

Neuron 549 in Layer 6

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: 2.9455. Min Range: -2.9455

Max Act: 2.9455. Min Act: -0.1700

Data Index: 788820 (Open Web Text)

Max Activating Token Index: 967

Text #1

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.9151. Min Act: -0.1700

Data Index: 4245121 (Open Web Text)

Max Activating Token Index: 509

Text #2

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.9148. Min Act: -0.1700

Data Index: 5969842 (Open Web Text)

Max Activating Token Index: 535

Text #3

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.8734. Min Act: -0.1700

Data Index: 5283408 (Open Web Text)

Max Activating Token Index: 273

Text #4

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.8689. Min Act: -0.1700

Data Index: 7658113 (Open Web Text)

Max Activating Token Index: 638

Text #5

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.8152. Min Act: -0.1700

Data Index: 8329246 (Open Web Text)

Max Activating Token Index: 534

Text #6

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.8108. Min Act: -0.1700

Data Index: 795938 (Open Web Text)

Max Activating Token Index: 356

Text #7

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.7957. Min Act: -0.1700

Data Index: 1006707 (Open Web Text)

Max Activating Token Index: 953

Text #8

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.7689. Min Act: -0.1700

Data Index: 2058815 (Open Web Text)

Max Activating Token Index: 896

Text #9

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.7818. Min Act: -0.1700

Data Index: 3810138 (Open Web Text)

Max Activating Token Index: 907

Text #10

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.7630. Min Act: -0.1700

Data Index: 3745642 (Open Web Text)

Max Activating Token Index: 132

Text #11

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.7652. Min Act: -0.1700

Data Index: 6692459 (Open Web Text)

Max Activating Token Index: 463

Text #12

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.7653. Min Act: -0.1700

Data Index: 2058945 (Open Web Text)

Max Activating Token Index: 729

Text #13

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.7570. Min Act: -0.1700

Data Index: 1462898 (Open Web Text)

Max Activating Token Index: 894

Text #14

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.7694. Min Act: -0.1700

Data Index: 2274700 (Open Web Text)

Max Activating Token Index: 681

Text #15

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.7489. Min Act: -0.1700

Data Index: 499759 (Open Web Text)

Max Activating Token Index: 579

Text #16

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.7386. Min Act: -0.1700

Data Index: 6038238 (Open Web Text)

Max Activating Token Index: 206

Text #17

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.7463. Min Act: -0.1700

Data Index: 8013733 (Open Web Text)

Max Activating Token Index: 914

Text #18

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.7328. Min Act: -0.1700

Data Index: 550281 (Open Web Text)

Max Activating Token Index: 573

Text #19

Max Range: 2.9455. Min Range: -2.9455

Max Act: 2.6921. Min Act: -0.1700

Data Index: 2119703 (Open Web Text)

Max Activating Token Index: 421