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

Dataset: Open Web Text

Neuron 2761 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: 3.0140. Min Range: -3.0140

Max Act: 3.0140. Min Act: -0.1700

Data Index: 651187 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 3.0140. Min Range: -3.0140

Max Act: 3.0054. Min Act: -0.1700

Data Index: 3509902 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9995. Min Act: -0.1700

Data Index: 7272233 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9670. Min Act: -0.1700

Data Index: 4483556 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9647. Min Act: -0.1700

Data Index: 8742773 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9370. Min Act: -0.1700

Data Index: 2024081 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9370. Min Act: -0.1700

Data Index: 8641511 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9332. Min Act: -0.1700

Data Index: 7064627 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9370. Min Act: -0.1700

Data Index: 8641436 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9437. Min Act: -0.1700

Data Index: 8254294 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9370. Min Act: -0.1700

Data Index: 6518840 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9370. Min Act: -0.1700

Data Index: 7853079 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9370. Min Act: -0.1700

Data Index: 5707487 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9370. Min Act: -0.1700

Data Index: 2957648 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9370. Min Act: -0.1700

Data Index: 7072379 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9370. Min Act: -0.1700

Data Index: 538658 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9370. Min Act: -0.1700

Data Index: 489119 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9424. Min Act: -0.1700

Data Index: 2643206 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9370. Min Act: -0.1700

Data Index: 4188060 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.0140. Min Range: -3.0140

Max Act: 2.9387. Min Act: -0.1700

Data Index: 4079268 (Open Web Text)

Max Activating Token Index: 3