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

Dataset: Open Web Text

Neuron 2273 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: 3.1206. Min Range: -3.1206

Max Act: 3.1206. Min Act: -0.1700

Data Index: 7130465 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.1206. Min Range: -3.1206

Max Act: 3.0397. Min Act: -0.1700

Data Index: 7284089 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 3.1206. Min Range: -3.1206

Max Act: 3.0188. Min Act: -0.1700

Data Index: 5709401 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 3.1206. Min Range: -3.1206

Max Act: 3.0319. Min Act: -0.1700

Data Index: 3414631 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.1206. Min Range: -3.1206

Max Act: 2.9978. Min Act: -0.1700

Data Index: 6698231 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 3.1206. Min Range: -3.1206

Max Act: 3.0039. Min Act: -0.1700

Data Index: 539942 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.1206. Min Range: -3.1206

Max Act: 2.9850. Min Act: -0.1700

Data Index: 8086827 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.1206. Min Range: -3.1206

Max Act: 2.9397. Min Act: -0.1700

Data Index: 2363232 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.1206. Min Range: -3.1206

Max Act: 2.9448. Min Act: -0.1700

Data Index: 1868219 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 3.1206. Min Range: -3.1206

Max Act: 2.9246. Min Act: -0.1700

Data Index: 5321272 (Open Web Text)

Max Activating Token Index: 28

Text #10

Max Range: 3.1206. Min Range: -3.1206

Max Act: 2.9135. Min Act: -0.1700

Data Index: 7644696 (Open Web Text)

Max Activating Token Index: 15

Text #11

Max Range: 3.1206. Min Range: -3.1206

Max Act: 2.9149. Min Act: -0.1700

Data Index: 135971 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.1206. Min Range: -3.1206

Max Act: 2.9142. Min Act: -0.1700

Data Index: 6189852 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 3.1206. Min Range: -3.1206

Max Act: 2.9048. Min Act: -0.1700

Data Index: 7173174 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 3.1206. Min Range: -3.1206

Max Act: 2.8879. Min Act: -0.1700

Data Index: 2384713 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 3.1206. Min Range: -3.1206

Max Act: 2.8863. Min Act: -0.1700

Data Index: 7498039 (Open Web Text)

Max Activating Token Index: 825

Text #16

Max Range: 3.1206. Min Range: -3.1206

Max Act: 2.9100. Min Act: -0.1700

Data Index: 7571261 (Open Web Text)

Max Activating Token Index: 24

Text #17

Max Range: 3.1206. Min Range: -3.1206

Max Act: 2.8974. Min Act: -0.1700

Data Index: 1775834 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.1206. Min Range: -3.1206

Max Act: 2.8856. Min Act: -0.1700

Data Index: 3797920 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 3.1206. Min Range: -3.1206

Max Act: 2.9017. Min Act: -0.1700

Data Index: 7584876 (Open Web Text)

Max Activating Token Index: 3