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

Dataset: Open Web Text

Neuron 2142 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: 0.7201. Min Range: -0.7201

Max Act: 0.7201. Min Act: -0.1700

Data Index: 2127478 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.6210. Min Act: -0.1700

Data Index: 1737436 (Open Web Text)

Max Activating Token Index: 15

Text #2

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.6072. Min Act: -0.1700

Data Index: 7305900 (Open Web Text)

Max Activating Token Index: 40

Text #3

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5895. Min Act: -0.1700

Data Index: 3381806 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5912. Min Act: -0.1700

Data Index: 4568060 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5903. Min Act: -0.1700

Data Index: 4519644 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5834. Min Act: -0.1700

Data Index: 3120527 (Open Web Text)

Max Activating Token Index: 1004

Text #7

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5673. Min Act: -0.1700

Data Index: 5230911 (Open Web Text)

Max Activating Token Index: 1000

Text #8

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5867. Min Act: -0.1700

Data Index: 8365934 (Open Web Text)

Max Activating Token Index: 98

Text #9

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5832. Min Act: -0.1690

Data Index: 3051531 (Open Web Text)

Max Activating Token Index: 41

Text #10

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5702. Min Act: -0.1700

Data Index: 246436 (Open Web Text)

Max Activating Token Index: 164

Text #11

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5604. Min Act: -0.1700

Data Index: 2571121 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5771. Min Act: -0.1700

Data Index: 5028917 (Open Web Text)

Max Activating Token Index: 961

Text #13

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5712. Min Act: -0.1700

Data Index: 6739870 (Open Web Text)

Max Activating Token Index: 90

Text #14

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5624. Min Act: -0.1700

Data Index: 4336305 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5659. Min Act: -0.1700

Data Index: 7350692 (Open Web Text)

Max Activating Token Index: 158

Text #16

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5457. Min Act: -0.1700

Data Index: 7901221 (Open Web Text)

Max Activating Token Index: 1017

Text #17

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5504. Min Act: -0.1700

Data Index: 2180909 (Open Web Text)

Max Activating Token Index: 927

Text #18

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5542. Min Act: -0.1699

Data Index: 5063037 (Open Web Text)

Max Activating Token Index: 382

Text #19

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5486. Min Act: -0.1700

Data Index: 2663707 (Open Web Text)

Max Activating Token Index: 1018