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

Dataset: Open Web Text

Neuron 436 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: 3.8889. Min Range: -3.8889

Max Act: 3.8889. Min Act: -0.1700

Data Index: 8054934 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.8889. Min Range: -3.8889

Max Act: 3.8652. Min Act: -0.1700

Data Index: 8740016 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.8889. Min Range: -3.8889

Max Act: 3.8318. Min Act: -0.1700

Data Index: 8043629 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 3.8889. Min Range: -3.8889

Max Act: 3.8331. Min Act: -0.1700

Data Index: 8556245 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.8889. Min Range: -3.8889

Max Act: 3.7972. Min Act: -0.1700

Data Index: 8793521 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.8889. Min Range: -3.8889

Max Act: 3.7616. Min Act: -0.1700

Data Index: 4669958 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.8889. Min Range: -3.8889

Max Act: 3.7831. Min Act: -0.1700

Data Index: 3115511 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.8889. Min Range: -3.8889

Max Act: 3.7567. Min Act: -0.1700

Data Index: 1291505 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.8889. Min Range: -3.8889

Max Act: 3.7662. Min Act: -0.1700

Data Index: 5579848 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.8889. Min Range: -3.8889

Max Act: 3.7616. Min Act: -0.1700

Data Index: 6319251 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.8889. Min Range: -3.8889

Max Act: 3.7638. Min Act: -0.1700

Data Index: 4053028 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.8889. Min Range: -3.8889

Max Act: 3.7567. Min Act: -0.1700

Data Index: 1552332 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.8889. Min Range: -3.8889

Max Act: 3.7298. Min Act: -0.1700

Data Index: 6768269 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.8889. Min Range: -3.8889

Max Act: 3.7366. Min Act: -0.1700

Data Index: 1805075 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.8889. Min Range: -3.8889

Max Act: 3.7517. Min Act: -0.1700

Data Index: 2489232 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.8889. Min Range: -3.8889

Max Act: 3.7447. Min Act: -0.1700

Data Index: 3531055 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.8889. Min Range: -3.8889

Max Act: 3.7525. Min Act: -0.1700

Data Index: 1124259 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.8889. Min Range: -3.8889

Max Act: 3.7261. Min Act: -0.1700

Data Index: 3989529 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 3.8889. Min Range: -3.8889

Max Act: 3.7330. Min Act: -0.1700

Data Index: 2822917 (Open Web Text)

Max Activating Token Index: 29

Text #19

Max Range: 3.8889. Min Range: -3.8889

Max Act: 3.7414. Min Act: -0.1700

Data Index: 2749505 (Open Web Text)

Max Activating Token Index: 3