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

Dataset: Open Web Text

Neuron 443 in Layer 2

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: 4.2414. Min Range: -4.2414

Max Act: 4.2414. Min Act: -0.1700

Data Index: 628342 (Open Web Text)

Max Activating Token Index: 540

Text #1

Max Range: 4.2414. Min Range: -4.2414

Max Act: 4.1776. Min Act: -0.1700

Data Index: 6194053 (Open Web Text)

Max Activating Token Index: 293

Text #2

Max Range: 4.2414. Min Range: -4.2414

Max Act: 4.1680. Min Act: -0.1700

Data Index: 1400881 (Open Web Text)

Max Activating Token Index: 79

Text #3

Max Range: 4.2414. Min Range: -4.2414

Max Act: 4.1591. Min Act: -0.1700

Data Index: 5407910 (Open Web Text)

Max Activating Token Index: 381

Text #4

Max Range: 4.2414. Min Range: -4.2414

Max Act: 4.1481. Min Act: -0.1700

Data Index: 6709947 (Open Web Text)

Max Activating Token Index: 870

Text #5

Max Range: 4.2414. Min Range: -4.2414

Max Act: 4.1377. Min Act: -0.1700

Data Index: 7616748 (Open Web Text)

Max Activating Token Index: 386

Text #6

Max Range: 4.2414. Min Range: -4.2414

Max Act: 4.1331. Min Act: -0.1700

Data Index: 4484128 (Open Web Text)

Max Activating Token Index: 96

Text #7

Max Range: 4.2414. Min Range: -4.2414

Max Act: 4.1570. Min Act: -0.1700

Data Index: 299622 (Open Web Text)

Max Activating Token Index: 506

Text #8

Max Range: 4.2414. Min Range: -4.2414

Max Act: 4.1142. Min Act: -0.1700

Data Index: 4873733 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.2414. Min Range: -4.2414

Max Act: 4.1119. Min Act: -0.1700

Data Index: 7602145 (Open Web Text)

Max Activating Token Index: 73

Text #10

Max Range: 4.2414. Min Range: -4.2414

Max Act: 4.1197. Min Act: -0.1700

Data Index: 6681298 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.2414. Min Range: -4.2414

Max Act: 4.1143. Min Act: -0.1700

Data Index: 5090609 (Open Web Text)

Max Activating Token Index: 331

Text #12

Max Range: 4.2414. Min Range: -4.2414

Max Act: 4.0993. Min Act: -0.1700

Data Index: 8381695 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.2414. Min Range: -4.2414

Max Act: 4.1137. Min Act: -0.1700

Data Index: 102093 (Open Web Text)

Max Activating Token Index: 61

Text #14

Max Range: 4.2414. Min Range: -4.2414

Max Act: 4.1140. Min Act: -0.1700

Data Index: 3565420 (Open Web Text)

Max Activating Token Index: 387

Text #15

Max Range: 4.2414. Min Range: -4.2414

Max Act: 4.0951. Min Act: -0.1700

Data Index: 791421 (Open Web Text)

Max Activating Token Index: 628

Text #16

Max Range: 4.2414. Min Range: -4.2414

Max Act: 4.1039. Min Act: -0.1700

Data Index: 4528855 (Open Web Text)

Max Activating Token Index: 913

Text #17

Max Range: 4.2414. Min Range: -4.2414

Max Act: 4.0801. Min Act: -0.1700

Data Index: 1018517 (Open Web Text)

Max Activating Token Index: 812

Text #18

Max Range: 4.2414. Min Range: -4.2414

Max Act: 4.0792. Min Act: -0.1700

Data Index: 1294959 (Open Web Text)

Max Activating Token Index: 216

Text #19

Max Range: 4.2414. Min Range: -4.2414

Max Act: 4.0814. Min Act: -0.1700

Data Index: 4217736 (Open Web Text)

Max Activating Token Index: 281