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

Dataset: Open Web Text

Neuron 973 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: 4.1671. Min Range: -4.1671

Max Act: 4.1671. Min Act: -0.1700

Data Index: 2086902 (Open Web Text)

Max Activating Token Index: 49

Text #1

Max Range: 4.1671. Min Range: -4.1671

Max Act: 4.1104. Min Act: -0.1700

Data Index: 3992780 (Open Web Text)

Max Activating Token Index: 66

Text #2

Max Range: 4.1671. Min Range: -4.1671

Max Act: 4.0223. Min Act: -0.1700

Data Index: 879622 (Open Web Text)

Max Activating Token Index: 175

Text #3

Max Range: 4.1671. Min Range: -4.1671

Max Act: 4.0211. Min Act: -0.1700

Data Index: 2334031 (Open Web Text)

Max Activating Token Index: 162

Text #4

Max Range: 4.1671. Min Range: -4.1671

Max Act: 4.0360. Min Act: -0.1700

Data Index: 5406773 (Open Web Text)

Max Activating Token Index: 385

Text #5

Max Range: 4.1671. Min Range: -4.1671

Max Act: 3.9759. Min Act: -0.1700

Data Index: 8791688 (Open Web Text)

Max Activating Token Index: 70

Text #6

Max Range: 4.1671. Min Range: -4.1671

Max Act: 4.0005. Min Act: -0.1700

Data Index: 3485214 (Open Web Text)

Max Activating Token Index: 906

Text #7

Max Range: 4.1671. Min Range: -4.1671

Max Act: 3.9382. Min Act: -0.1700

Data Index: 1535439 (Open Web Text)

Max Activating Token Index: 706

Text #8

Max Range: 4.1671. Min Range: -4.1671

Max Act: 3.9874. Min Act: -0.1700

Data Index: 3068323 (Open Web Text)

Max Activating Token Index: 575

Text #9

Max Range: 4.1671. Min Range: -4.1671

Max Act: 3.9176. Min Act: -0.1700

Data Index: 3226771 (Open Web Text)

Max Activating Token Index: 445

Text #10

Max Range: 4.1671. Min Range: -4.1671

Max Act: 3.9407. Min Act: -0.1700

Data Index: 8627199 (Open Web Text)

Max Activating Token Index: 807

Text #11

Max Range: 4.1671. Min Range: -4.1671

Max Act: 3.9552. Min Act: -0.1700

Data Index: 313145 (Open Web Text)

Max Activating Token Index: 427

Text #12

Max Range: 4.1671. Min Range: -4.1671

Max Act: 3.9087. Min Act: -0.1700

Data Index: 3618260 (Open Web Text)

Max Activating Token Index: 751

Text #13

Max Range: 4.1671. Min Range: -4.1671

Max Act: 3.9150. Min Act: -0.1700

Data Index: 7292555 (Open Web Text)

Max Activating Token Index: 972

Text #14

Max Range: 4.1671. Min Range: -4.1671

Max Act: 3.9184. Min Act: -0.1700

Data Index: 879621 (Open Web Text)

Max Activating Token Index: 804

Text #15

Max Range: 4.1671. Min Range: -4.1671

Max Act: 3.8969. Min Act: -0.1700

Data Index: 3992779 (Open Web Text)

Max Activating Token Index: 707

Text #16

Max Range: 4.1671. Min Range: -4.1671

Max Act: 3.9127. Min Act: -0.1700

Data Index: 7552672 (Open Web Text)

Max Activating Token Index: 818

Text #17

Max Range: 4.1671. Min Range: -4.1671

Max Act: 3.9015. Min Act: -0.1700

Data Index: 4420819 (Open Web Text)

Max Activating Token Index: 106

Text #18

Max Range: 4.1671. Min Range: -4.1671

Max Act: 3.9110. Min Act: -0.1700

Data Index: 6078650 (Open Web Text)

Max Activating Token Index: 126

Text #19

Max Range: 4.1671. Min Range: -4.1671

Max Act: 3.9032. Min Act: -0.1700

Data Index: 2688095 (Open Web Text)

Max Activating Token Index: 740