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

Dataset: Open Web Text

Neuron 594 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: 3.4106. Min Range: -3.4106

Max Act: 3.4106. Min Act: -0.1700

Data Index: 8623831 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.4106. Min Act: -0.1700

Data Index: 8629839 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.4106. Min Act: -0.1700

Data Index: 3879821 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.4106. Min Act: -0.1700

Data Index: 1279804 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.3474. Min Act: -0.1700

Data Index: 2725313 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.2814. Min Act: -0.1700

Data Index: 4646303 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.2495. Min Act: -0.1700

Data Index: 4313615 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.2369. Min Act: -0.1700

Data Index: 8702384 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.1911. Min Act: -0.1700

Data Index: 4484645 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.1660. Min Act: -0.1700

Data Index: 3245943 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.1755. Min Act: -0.1700

Data Index: 1110813 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.1673. Min Act: -0.1700

Data Index: 1615309 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.1673. Min Act: -0.1700

Data Index: 665372 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.1673. Min Act: -0.1700

Data Index: 4317750 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.1537. Min Act: -0.1700

Data Index: 5692728 (Open Web Text)

Max Activating Token Index: 49

Text #15

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.1673. Min Act: -0.1700

Data Index: 3889272 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.1673. Min Act: -0.1700

Data Index: 8667779 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.1673. Min Act: -0.1700

Data Index: 3813307 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.1673. Min Act: -0.1700

Data Index: 2027027 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.4106. Min Range: -3.4106

Max Act: 3.1411. Min Act: -0.1700

Data Index: 3441218 (Open Web Text)

Max Activating Token Index: 11