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

Dataset: Open Web Text

Neuron 72 in Layer 2

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: 3.9763. Min Range: -3.9763

Max Act: 3.9763. Min Act: -0.1700

Data Index: 8179106 (Open Web Text)

Max Activating Token Index: 640

Text #1

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.8394. Min Act: -0.1700

Data Index: 2419305 (Open Web Text)

Max Activating Token Index: 736

Text #2

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.7963. Min Act: -0.1700

Data Index: 4988918 (Open Web Text)

Max Activating Token Index: 923

Text #3

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.8137. Min Act: -0.1700

Data Index: 4420126 (Open Web Text)

Max Activating Token Index: 779

Text #4

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.7923. Min Act: -0.1700

Data Index: 506364 (Open Web Text)

Max Activating Token Index: 51

Text #5

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.7570. Min Act: -0.1700

Data Index: 832496 (Open Web Text)

Max Activating Token Index: 902

Text #6

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.7255. Min Act: -0.1700

Data Index: 645669 (Open Web Text)

Max Activating Token Index: 847

Text #7

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.7323. Min Act: -0.1700

Data Index: 4144470 (Open Web Text)

Max Activating Token Index: 55

Text #8

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.7173. Min Act: -0.1700

Data Index: 6296984 (Open Web Text)

Max Activating Token Index: 33

Text #9

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.7339. Min Act: -0.1700

Data Index: 6989968 (Open Web Text)

Max Activating Token Index: 166

Text #10

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.6951. Min Act: -0.1700

Data Index: 8448391 (Open Web Text)

Max Activating Token Index: 90

Text #11

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.7133. Min Act: -0.1700

Data Index: 3165089 (Open Web Text)

Max Activating Token Index: 467

Text #12

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.7060. Min Act: -0.1700

Data Index: 4483011 (Open Web Text)

Max Activating Token Index: 52

Text #13

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.6751. Min Act: -0.1700

Data Index: 5734634 (Open Web Text)

Max Activating Token Index: 532

Text #14

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.6886. Min Act: -0.1700

Data Index: 7682800 (Open Web Text)

Max Activating Token Index: 622

Text #15

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.6723. Min Act: -0.1700

Data Index: 4483337 (Open Web Text)

Max Activating Token Index: 617

Text #16

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.6717. Min Act: -0.1700

Data Index: 5816478 (Open Web Text)

Max Activating Token Index: 983

Text #17

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.6559. Min Act: -0.1700

Data Index: 506363 (Open Web Text)

Max Activating Token Index: 78

Text #18

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.6573. Min Act: -0.1700

Data Index: 1738633 (Open Web Text)

Max Activating Token Index: 115

Text #19

Max Range: 3.9763. Min Range: -3.9763

Max Act: 3.6652. Min Act: -0.1700

Data Index: 4256818 (Open Web Text)

Max Activating Token Index: 171