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

Dataset: Open Web Text

Neuron 501 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: 4.4066. Min Range: -4.4066

Max Act: 4.4066. Min Act: -0.1700

Data Index: 5568947 (Open Web Text)

Max Activating Token Index: 988

Text #1

Max Range: 4.4066. Min Range: -4.4066

Max Act: 4.3852. Min Act: -0.1700

Data Index: 2232000 (Open Web Text)

Max Activating Token Index: 640

Text #2

Max Range: 4.4066. Min Range: -4.4066

Max Act: 4.3122. Min Act: -0.1700

Data Index: 2899092 (Open Web Text)

Max Activating Token Index: 68

Text #3

Max Range: 4.4066. Min Range: -4.4066

Max Act: 4.2903. Min Act: -0.1700

Data Index: 1361395 (Open Web Text)

Max Activating Token Index: 483

Text #4

Max Range: 4.4066. Min Range: -4.4066

Max Act: 4.2939. Min Act: -0.1700

Data Index: 7492639 (Open Web Text)

Max Activating Token Index: 931

Text #5

Max Range: 4.4066. Min Range: -4.4066

Max Act: 4.2941. Min Act: -0.1700

Data Index: 6558492 (Open Web Text)

Max Activating Token Index: 666

Text #6

Max Range: 4.4066. Min Range: -4.4066

Max Act: 4.2458. Min Act: -0.1700

Data Index: 6644633 (Open Web Text)

Max Activating Token Index: 529

Text #7

Max Range: 4.4066. Min Range: -4.4066

Max Act: 4.3141. Min Act: -0.1700

Data Index: 6843425 (Open Web Text)

Max Activating Token Index: 544

Text #8

Max Range: 4.4066. Min Range: -4.4066

Max Act: 4.2283. Min Act: -0.1700

Data Index: 3048758 (Open Web Text)

Max Activating Token Index: 663

Text #9

Max Range: 4.4066. Min Range: -4.4066

Max Act: 4.2272. Min Act: -0.1700

Data Index: 1356773 (Open Web Text)

Max Activating Token Index: 624

Text #10

Max Range: 4.4066. Min Range: -4.4066

Max Act: 4.2568. Min Act: -0.1700

Data Index: 2643901 (Open Web Text)

Max Activating Token Index: 223

Text #11

Max Range: 4.4066. Min Range: -4.4066

Max Act: 4.2700. Min Act: -0.1700

Data Index: 5104732 (Open Web Text)

Max Activating Token Index: 152

Text #12

Max Range: 4.4066. Min Range: -4.4066

Max Act: 4.1958. Min Act: -0.1700

Data Index: 8707875 (Open Web Text)

Max Activating Token Index: 997

Text #13

Max Range: 4.4066. Min Range: -4.4066

Max Act: 4.1755. Min Act: -0.1700

Data Index: 7557577 (Open Web Text)

Max Activating Token Index: 659

Text #14

Max Range: 4.4066. Min Range: -4.4066

Max Act: 4.2331. Min Act: -0.1700

Data Index: 1069006 (Open Web Text)

Max Activating Token Index: 647

Text #15

Max Range: 4.4066. Min Range: -4.4066

Max Act: 4.1664. Min Act: -0.1700

Data Index: 4139913 (Open Web Text)

Max Activating Token Index: 422

Text #16

Max Range: 4.4066. Min Range: -4.4066

Max Act: 4.1757. Min Act: -0.1700

Data Index: 7423618 (Open Web Text)

Max Activating Token Index: 639

Text #17

Max Range: 4.4066. Min Range: -4.4066

Max Act: 4.1525. Min Act: -0.1700

Data Index: 7356649 (Open Web Text)

Max Activating Token Index: 105

Text #18

Max Range: 4.4066. Min Range: -4.4066

Max Act: 4.1774. Min Act: -0.1700

Data Index: 7348636 (Open Web Text)

Max Activating Token Index: 735

Text #19

Max Range: 4.4066. Min Range: -4.4066

Max Act: 4.2876. Min Act: -0.1700

Data Index: 2652685 (Open Web Text)

Max Activating Token Index: 244