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

Dataset: Open Web Text

Neuron 2632 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: 1.2223. Min Range: -1.2223

Max Act: 1.2223. Min Act: -0.1700

Data Index: 1219535 (Open Web Text)

Max Activating Token Index: 61

Text #1

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1904. Min Act: -0.1700

Data Index: 7523476 (Open Web Text)

Max Activating Token Index: 61

Text #2

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1831. Min Act: -0.1700

Data Index: 4809347 (Open Web Text)

Max Activating Token Index: 56

Text #3

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1814. Min Act: -0.1700

Data Index: 7500938 (Open Web Text)

Max Activating Token Index: 52

Text #4

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1699. Min Act: -0.1700

Data Index: 3666256 (Open Web Text)

Max Activating Token Index: 61

Text #5

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1788. Min Act: -0.1700

Data Index: 4019197 (Open Web Text)

Max Activating Token Index: 69

Text #6

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1729. Min Act: -0.1700

Data Index: 3406317 (Open Web Text)

Max Activating Token Index: 61

Text #7

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1700. Min Act: -0.1700

Data Index: 6976227 (Open Web Text)

Max Activating Token Index: 62

Text #8

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1728. Min Act: -0.1700

Data Index: 5078164 (Open Web Text)

Max Activating Token Index: 60

Text #9

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1699. Min Act: -0.1700

Data Index: 2409366 (Open Web Text)

Max Activating Token Index: 50

Text #10

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1613. Min Act: -0.1700

Data Index: 3618734 (Open Web Text)

Max Activating Token Index: 60

Text #11

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1613. Min Act: -0.1700

Data Index: 6014021 (Open Web Text)

Max Activating Token Index: 51

Text #12

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1624. Min Act: -0.1700

Data Index: 5424260 (Open Web Text)

Max Activating Token Index: 57

Text #13

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1628. Min Act: -0.1700

Data Index: 8232725 (Open Web Text)

Max Activating Token Index: 53

Text #14

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1646. Min Act: -0.1700

Data Index: 7351380 (Open Web Text)

Max Activating Token Index: 63

Text #15

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1684. Min Act: -0.1700

Data Index: 716574 (Open Web Text)

Max Activating Token Index: 60

Text #16

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1704. Min Act: -0.1700

Data Index: 3904304 (Open Web Text)

Max Activating Token Index: 58

Text #17

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1601. Min Act: -0.1700

Data Index: 3132165 (Open Web Text)

Max Activating Token Index: 69

Text #18

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1573. Min Act: -0.1700

Data Index: 1767885 (Open Web Text)

Max Activating Token Index: 64

Text #19

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1548. Min Act: -0.1700

Data Index: 2112398 (Open Web Text)

Max Activating Token Index: 55