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

Dataset: Open Web Text

Neuron 3049 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: 2.3068. Min Range: -2.3068

Max Act: 2.3019. Min Act: -0.1700

Data Index: 7426351 (Open Web Text)

Max Activating Token Index: 705

Text #1

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.3068. Min Act: -0.1700

Data Index: 4344681 (Open Web Text)

Max Activating Token Index: 674

Text #2

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.2696. Min Act: -0.1700

Data Index: 2566965 (Open Web Text)

Max Activating Token Index: 553

Text #3

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.2647. Min Act: -0.1700

Data Index: 8549655 (Open Web Text)

Max Activating Token Index: 657

Text #4

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.2522. Min Act: -0.1700

Data Index: 7707180 (Open Web Text)

Max Activating Token Index: 928

Text #5

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.2211. Min Act: -0.1690

Data Index: 7158735 (Open Web Text)

Max Activating Token Index: 282

Text #6

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.2396. Min Act: -0.1700

Data Index: 44492 (Open Web Text)

Max Activating Token Index: 795

Text #7

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.2341. Min Act: -0.1700

Data Index: 6941045 (Open Web Text)

Max Activating Token Index: 944

Text #8

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.2210. Min Act: -0.1700

Data Index: 8790725 (Open Web Text)

Max Activating Token Index: 442

Text #9

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.2159. Min Act: -0.1696

Data Index: 5492191 (Open Web Text)

Max Activating Token Index: 340

Text #10

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.1961. Min Act: -0.1700

Data Index: 6181800 (Open Web Text)

Max Activating Token Index: 564

Text #11

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.2090. Min Act: -0.1700

Data Index: 196203 (Open Web Text)

Max Activating Token Index: 871

Text #12

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.1973. Min Act: -0.1700

Data Index: 8184180 (Open Web Text)

Max Activating Token Index: 75

Text #13

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.1789. Min Act: -0.1699

Data Index: 2591122 (Open Web Text)

Max Activating Token Index: 934

Text #14

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.1757. Min Act: -0.1700

Data Index: 4024830 (Open Web Text)

Max Activating Token Index: 748

Text #15

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.1913. Min Act: -0.1678

Data Index: 2249482 (Open Web Text)

Max Activating Token Index: 517

Text #16

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.1612. Min Act: -0.1700

Data Index: 3291792 (Open Web Text)

Max Activating Token Index: 331

Text #17

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.1441. Min Act: -0.1700

Data Index: 6145654 (Open Web Text)

Max Activating Token Index: 644

Text #18

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.1605. Min Act: -0.1699

Data Index: 6833978 (Open Web Text)

Max Activating Token Index: 638

Text #19

Max Range: 2.3068. Min Range: -2.3068

Max Act: 2.1444. Min Act: -0.1694

Data Index: 2902237 (Open Web Text)

Max Activating Token Index: 797