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

Dataset: Open Web Text

Neuron 1993 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: 4.4216. Min Range: -4.4216

Max Act: 4.4216. Min Act: -0.1700

Data Index: 6283761 (Open Web Text)

Max Activating Token Index: 38

Text #1

Max Range: 4.4216. Min Range: -4.4216

Max Act: 4.3878. Min Act: -0.1700

Data Index: 284608 (Open Web Text)

Max Activating Token Index: 22

Text #2

Max Range: 4.4216. Min Range: -4.4216

Max Act: 4.2880. Min Act: -0.1700

Data Index: 2571765 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 4.4216. Min Range: -4.4216

Max Act: 4.2950. Min Act: -0.1700

Data Index: 1103212 (Open Web Text)

Max Activating Token Index: 390

Text #4

Max Range: 4.4216. Min Range: -4.4216

Max Act: 4.2509. Min Act: -0.1700

Data Index: 5961774 (Open Web Text)

Max Activating Token Index: 27

Text #5

Max Range: 4.4216. Min Range: -4.4216

Max Act: 4.1451. Min Act: -0.1700

Data Index: 3753051 (Open Web Text)

Max Activating Token Index: 56

Text #6

Max Range: 4.4216. Min Range: -4.4216

Max Act: 4.1338. Min Act: -0.1700

Data Index: 6034514 (Open Web Text)

Max Activating Token Index: 57

Text #7

Max Range: 4.4216. Min Range: -4.4216

Max Act: 4.1486. Min Act: -0.1700

Data Index: 2716276 (Open Web Text)

Max Activating Token Index: 33

Text #8

Max Range: 4.4216. Min Range: -4.4216

Max Act: 4.1152. Min Act: -0.1700

Data Index: 1020126 (Open Web Text)

Max Activating Token Index: 23

Text #9

Max Range: 4.4216. Min Range: -4.4216

Max Act: 4.1081. Min Act: -0.1700

Data Index: 1550552 (Open Web Text)

Max Activating Token Index: 798

Text #10

Max Range: 4.4216. Min Range: -4.4216

Max Act: 4.0651. Min Act: -0.1700

Data Index: 3480490 (Open Web Text)

Max Activating Token Index: 668

Text #11

Max Range: 4.4216. Min Range: -4.4216

Max Act: 4.0599. Min Act: -0.1700

Data Index: 4522389 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 4.4216. Min Range: -4.4216

Max Act: 4.0618. Min Act: -0.1700

Data Index: 415977 (Open Web Text)

Max Activating Token Index: 82

Text #13

Max Range: 4.4216. Min Range: -4.4216

Max Act: 4.0204. Min Act: -0.1700

Data Index: 1447128 (Open Web Text)

Max Activating Token Index: 36

Text #14

Max Range: 4.4216. Min Range: -4.4216

Max Act: 4.0327. Min Act: -0.1700

Data Index: 7120917 (Open Web Text)

Max Activating Token Index: 18

Text #15

Max Range: 4.4216. Min Range: -4.4216

Max Act: 4.0284. Min Act: -0.1700

Data Index: 301128 (Open Web Text)

Max Activating Token Index: 82

Text #16

Max Range: 4.4216. Min Range: -4.4216

Max Act: 4.0174. Min Act: -0.1700

Data Index: 421719 (Open Web Text)

Max Activating Token Index: 16

Text #17

Max Range: 4.4216. Min Range: -4.4216

Max Act: 4.0066. Min Act: -0.1700

Data Index: 6148535 (Open Web Text)

Max Activating Token Index: 501

Text #18

Max Range: 4.4216. Min Range: -4.4216

Max Act: 3.9969. Min Act: -0.1700

Data Index: 4229447 (Open Web Text)

Max Activating Token Index: 75

Text #19

Max Range: 4.4216. Min Range: -4.4216

Max Act: 3.9816. Min Act: -0.1700

Data Index: 6365230 (Open Web Text)

Max Activating Token Index: 525