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

Dataset: Open Web Text

Neuron 2559 in Layer 1

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: 3.1937. Min Range: -3.1937

Max Act: 3.1937. Min Act: -0.1700

Data Index: 3159306 (Open Web Text)

Max Activating Token Index: 217

Text #1

Max Range: 3.1937. Min Range: -3.1937

Max Act: 3.1371. Min Act: -0.1700

Data Index: 842582 (Open Web Text)

Max Activating Token Index: 17

Text #2

Max Range: 3.1937. Min Range: -3.1937

Max Act: 3.0364. Min Act: -0.1700

Data Index: 7498010 (Open Web Text)

Max Activating Token Index: 425

Text #3

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.9727. Min Act: -0.1700

Data Index: 2906043 (Open Web Text)

Max Activating Token Index: 21

Text #4

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.9493. Min Act: -0.1700

Data Index: 2941119 (Open Web Text)

Max Activating Token Index: 25

Text #5

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.9613. Min Act: -0.1700

Data Index: 6617390 (Open Web Text)

Max Activating Token Index: 577

Text #6

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.9061. Min Act: -0.1700

Data Index: 4647937 (Open Web Text)

Max Activating Token Index: 15

Text #7

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.9282. Min Act: -0.1700

Data Index: 5035859 (Open Web Text)

Max Activating Token Index: 29

Text #8

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.8840. Min Act: -0.1700

Data Index: 2731233 (Open Web Text)

Max Activating Token Index: 13

Text #9

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.8840. Min Act: -0.1700

Data Index: 3921178 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.8999. Min Act: -0.1700

Data Index: 5332808 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.9016. Min Act: -0.1700

Data Index: 4192647 (Open Web Text)

Max Activating Token Index: 27

Text #12

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.9016. Min Act: -0.1700

Data Index: 4169559 (Open Web Text)

Max Activating Token Index: 27

Text #13

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.8919. Min Act: -0.1700

Data Index: 6446633 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.8627. Min Act: -0.1700

Data Index: 988950 (Open Web Text)

Max Activating Token Index: 27

Text #15

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.8191. Min Act: -0.1700

Data Index: 1581185 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.8191. Min Act: -0.1700

Data Index: 5147087 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.8636. Min Act: -0.1700

Data Index: 7467705 (Open Web Text)

Max Activating Token Index: 35

Text #18

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.8382. Min Act: -0.1700

Data Index: 4589260 (Open Web Text)

Max Activating Token Index: 24

Text #19

Max Range: 3.1937. Min Range: -3.1937

Max Act: 2.8500. Min Act: -0.1700

Data Index: 5842171 (Open Web Text)

Max Activating Token Index: 11