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

Dataset: Open Web Text

Neuron 1936 in Layer 4

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: 3.8158. Min Range: -3.8158

Max Act: 3.8158. Min Act: -0.1700

Data Index: 7319992 (Open Web Text)

Max Activating Token Index: 1017

Text #1

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.6713. Min Act: -0.1700

Data Index: 3194021 (Open Web Text)

Max Activating Token Index: 80

Text #2

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.6238. Min Act: -0.1700

Data Index: 8742980 (Open Web Text)

Max Activating Token Index: 214

Text #3

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.6130. Min Act: -0.1700

Data Index: 3199426 (Open Web Text)

Max Activating Token Index: 170

Text #4

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.6745. Min Act: -0.1700

Data Index: 1263644 (Open Web Text)

Max Activating Token Index: 301

Text #5

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.6487. Min Act: -0.1700

Data Index: 1097861 (Open Web Text)

Max Activating Token Index: 756

Text #6

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5740. Min Act: -0.1700

Data Index: 1883744 (Open Web Text)

Max Activating Token Index: 825

Text #7

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5532. Min Act: -0.1700

Data Index: 8641049 (Open Web Text)

Max Activating Token Index: 704

Text #8

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5842. Min Act: -0.1700

Data Index: 4443978 (Open Web Text)

Max Activating Token Index: 463

Text #9

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5194. Min Act: -0.1700

Data Index: 979336 (Open Web Text)

Max Activating Token Index: 404

Text #10

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5161. Min Act: -0.1700

Data Index: 7693713 (Open Web Text)

Max Activating Token Index: 86

Text #11

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.4702. Min Act: -0.1700

Data Index: 5795125 (Open Web Text)

Max Activating Token Index: 654

Text #12

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.4433. Min Act: -0.1700

Data Index: 2406322 (Open Web Text)

Max Activating Token Index: 701

Text #13

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5136. Min Act: -0.1700

Data Index: 8094416 (Open Web Text)

Max Activating Token Index: 894

Text #14

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5009. Min Act: -0.1700

Data Index: 4926994 (Open Web Text)

Max Activating Token Index: 497

Text #15

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.4303. Min Act: -0.1700

Data Index: 5558743 (Open Web Text)

Max Activating Token Index: 523

Text #16

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.4810. Min Act: -0.1700

Data Index: 6590843 (Open Web Text)

Max Activating Token Index: 791

Text #17

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.4543. Min Act: -0.1700

Data Index: 4199928 (Open Web Text)

Max Activating Token Index: 141

Text #18

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.4559. Min Act: -0.1700

Data Index: 5653301 (Open Web Text)

Max Activating Token Index: 888

Text #19

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.4096. Min Act: -0.1700

Data Index: 8417991 (Open Web Text)

Max Activating Token Index: 809