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

Dataset: Open Web Text

Neuron 3011 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: 3.1728. Min Range: -3.1728

Max Act: 3.1728. Min Act: -0.1700

Data Index: 3496414 (Open Web Text)

Max Activating Token Index: 39

Text #1

Max Range: 3.1728. Min Range: -3.1728

Max Act: 3.0733. Min Act: -0.1700

Data Index: 927859 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 3.1728. Min Range: -3.1728

Max Act: 3.0149. Min Act: -0.1700

Data Index: 3496413 (Open Web Text)

Max Activating Token Index: 954

Text #3

Max Range: 3.1728. Min Range: -3.1728

Max Act: 3.0096. Min Act: -0.1700

Data Index: 2193253 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.1728. Min Range: -3.1728

Max Act: 2.9638. Min Act: -0.1700

Data Index: 4389009 (Open Web Text)

Max Activating Token Index: 68

Text #5

Max Range: 3.1728. Min Range: -3.1728

Max Act: 2.9739. Min Act: -0.1700

Data Index: 5408182 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 3.1728. Min Range: -3.1728

Max Act: 2.9385. Min Act: -0.1700

Data Index: 653281 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 3.1728. Min Range: -3.1728

Max Act: 2.9484. Min Act: -0.1700

Data Index: 1373790 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.1728. Min Range: -3.1728

Max Act: 2.9404. Min Act: -0.1700

Data Index: 8463073 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 3.1728. Min Range: -3.1728

Max Act: 2.9282. Min Act: -0.1700

Data Index: 7493120 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.1728. Min Range: -3.1728

Max Act: 2.9356. Min Act: -0.1700

Data Index: 3214116 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.1728. Min Range: -3.1728

Max Act: 2.9294. Min Act: -0.1700

Data Index: 8160917 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.1728. Min Range: -3.1728

Max Act: 2.9351. Min Act: -0.1700

Data Index: 1829579 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 3.1728. Min Range: -3.1728

Max Act: 2.9161. Min Act: -0.1700

Data Index: 4343336 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 3.1728. Min Range: -3.1728

Max Act: 2.9142. Min Act: -0.1700

Data Index: 2988241 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.1728. Min Range: -3.1728

Max Act: 2.9135. Min Act: -0.1700

Data Index: 1789237 (Open Web Text)

Max Activating Token Index: 1012

Text #16

Max Range: 3.1728. Min Range: -3.1728

Max Act: 2.9084. Min Act: -0.1700

Data Index: 941734 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 3.1728. Min Range: -3.1728

Max Act: 2.9182. Min Act: -0.1700

Data Index: 2593953 (Open Web Text)

Max Activating Token Index: 39

Text #18

Max Range: 3.1728. Min Range: -3.1728

Max Act: 2.9098. Min Act: -0.1700

Data Index: 6208894 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.1728. Min Range: -3.1728

Max Act: 2.8964. Min Act: -0.1700

Data Index: 6161141 (Open Web Text)

Max Activating Token Index: 19