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

Dataset: Open Web Text

Neuron 2478 in Layer 4

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: 5.1798. Min Range: -5.1798

Max Act: 5.1798. Min Act: -0.1700

Data Index: 6116651 (Open Web Text)

Max Activating Token Index: 353

Text #1

Max Range: 5.1798. Min Range: -5.1798

Max Act: 5.1018. Min Act: -0.1700

Data Index: 5083230 (Open Web Text)

Max Activating Token Index: 404

Text #2

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.9823. Min Act: -0.1700

Data Index: 1407365 (Open Web Text)

Max Activating Token Index: 783

Text #3

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.9677. Min Act: -0.1700

Data Index: 906421 (Open Web Text)

Max Activating Token Index: 749

Text #4

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.9096. Min Act: -0.1700

Data Index: 7283691 (Open Web Text)

Max Activating Token Index: 197

Text #5

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.9255. Min Act: -0.1700

Data Index: 1646192 (Open Web Text)

Max Activating Token Index: 975

Text #6

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.9285. Min Act: -0.1700

Data Index: 731384 (Open Web Text)

Max Activating Token Index: 767

Text #7

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.8725. Min Act: -0.1700

Data Index: 1155382 (Open Web Text)

Max Activating Token Index: 626

Text #8

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.8281. Min Act: -0.1700

Data Index: 6598711 (Open Web Text)

Max Activating Token Index: 934

Text #9

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.7878. Min Act: -0.1700

Data Index: 3704762 (Open Web Text)

Max Activating Token Index: 383

Text #10

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.7721. Min Act: -0.1700

Data Index: 4095242 (Open Web Text)

Max Activating Token Index: 824

Text #11

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.7203. Min Act: -0.1700

Data Index: 4597570 (Open Web Text)

Max Activating Token Index: 403

Text #12

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.7481. Min Act: -0.1700

Data Index: 174308 (Open Web Text)

Max Activating Token Index: 768

Text #13

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.7444. Min Act: -0.1700

Data Index: 3237027 (Open Web Text)

Max Activating Token Index: 936

Text #14

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.7168. Min Act: -0.1700

Data Index: 7681560 (Open Web Text)

Max Activating Token Index: 241

Text #15

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.7191. Min Act: -0.1700

Data Index: 137988 (Open Web Text)

Max Activating Token Index: 94

Text #16

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.6831. Min Act: -0.1700

Data Index: 1620388 (Open Web Text)

Max Activating Token Index: 1012

Text #17

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.6659. Min Act: -0.1700

Data Index: 4052188 (Open Web Text)

Max Activating Token Index: 633

Text #18

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.6685. Min Act: -0.1700

Data Index: 7418071 (Open Web Text)

Max Activating Token Index: 905

Text #19

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.6564. Min Act: -0.1700

Data Index: 5424992 (Open Web Text)

Max Activating Token Index: 569