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

Dataset: Open Web Text

Neuron 1682 in Layer 0

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: 3.1536. Min Range: -3.1536

Max Act: 3.1536. Min Act: -0.1700

Data Index: 4365347 (Open Web Text)

Max Activating Token Index: 61

Text #1

Max Range: 3.1536. Min Range: -3.1536

Max Act: 3.0546. Min Act: -0.1700

Data Index: 7574355 (Open Web Text)

Max Activating Token Index: 122

Text #2

Max Range: 3.1536. Min Range: -3.1536

Max Act: 3.0611. Min Act: -0.1700

Data Index: 4885270 (Open Web Text)

Max Activating Token Index: 52

Text #3

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.9728. Min Act: -0.1700

Data Index: 7964230 (Open Web Text)

Max Activating Token Index: 128

Text #4

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.9652. Min Act: -0.1700

Data Index: 1897952 (Open Web Text)

Max Activating Token Index: 703

Text #5

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.9756. Min Act: -0.1700

Data Index: 3452513 (Open Web Text)

Max Activating Token Index: 103

Text #6

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.9446. Min Act: -0.1700

Data Index: 1502790 (Open Web Text)

Max Activating Token Index: 61

Text #7

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.9506. Min Act: -0.1700

Data Index: 1270770 (Open Web Text)

Max Activating Token Index: 173

Text #8

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.9343. Min Act: -0.1700

Data Index: 3703954 (Open Web Text)

Max Activating Token Index: 718

Text #9

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.9380. Min Act: -0.1700

Data Index: 1548951 (Open Web Text)

Max Activating Token Index: 528

Text #10

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.9313. Min Act: -0.1700

Data Index: 2436782 (Open Web Text)

Max Activating Token Index: 99

Text #11

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.9291. Min Act: -0.1700

Data Index: 1817099 (Open Web Text)

Max Activating Token Index: 282

Text #12

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.9414. Min Act: -0.1700

Data Index: 5719007 (Open Web Text)

Max Activating Token Index: 462

Text #13

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.9392. Min Act: -0.1700

Data Index: 8273856 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.9189. Min Act: -0.1700

Data Index: 1793522 (Open Web Text)

Max Activating Token Index: 344

Text #15

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.9285. Min Act: -0.1700

Data Index: 7505286 (Open Web Text)

Max Activating Token Index: 530

Text #16

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.9189. Min Act: -0.1700

Data Index: 6076355 (Open Web Text)

Max Activating Token Index: 100

Text #17

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.9136. Min Act: -0.1700

Data Index: 5937127 (Open Web Text)

Max Activating Token Index: 34

Text #18

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.9161. Min Act: -0.1700

Data Index: 1572737 (Open Web Text)

Max Activating Token Index: 146

Text #19

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.9107. Min Act: -0.1700

Data Index: 3695273 (Open Web Text)

Max Activating Token Index: 199