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

Dataset: Open Web Text

Neuron 2158 in Layer 5

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: 3.3392. Min Range: -3.3392

Max Act: 3.3392. Min Act: -0.1700

Data Index: 7707286 (Open Web Text)

Max Activating Token Index: 666

Text #1

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.3182. Min Act: -0.1700

Data Index: 2419710 (Open Web Text)

Max Activating Token Index: 431

Text #2

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.2490. Min Act: -0.1700

Data Index: 3655028 (Open Web Text)

Max Activating Token Index: 759

Text #3

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.2647. Min Act: -0.1700

Data Index: 6755293 (Open Web Text)

Max Activating Token Index: 792

Text #4

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.2472. Min Act: -0.1700

Data Index: 7845632 (Open Web Text)

Max Activating Token Index: 826

Text #5

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.2466. Min Act: -0.1700

Data Index: 5490282 (Open Web Text)

Max Activating Token Index: 801

Text #6

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.2352. Min Act: -0.1700

Data Index: 6912205 (Open Web Text)

Max Activating Token Index: 802

Text #7

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.2169. Min Act: -0.1700

Data Index: 2924986 (Open Web Text)

Max Activating Token Index: 756

Text #8

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.2068. Min Act: -0.1700

Data Index: 990050 (Open Web Text)

Max Activating Token Index: 448

Text #9

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.1948. Min Act: -0.1700

Data Index: 5756240 (Open Web Text)

Max Activating Token Index: 806

Text #10

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.2038. Min Act: -0.1700

Data Index: 2300755 (Open Web Text)

Max Activating Token Index: 292

Text #11

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.1817. Min Act: -0.1700

Data Index: 3361139 (Open Web Text)

Max Activating Token Index: 616

Text #12

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.1842. Min Act: -0.1700

Data Index: 8673298 (Open Web Text)

Max Activating Token Index: 91

Text #13

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.1872. Min Act: -0.1700

Data Index: 8533294 (Open Web Text)

Max Activating Token Index: 237

Text #14

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.1640. Min Act: -0.1700

Data Index: 4818372 (Open Web Text)

Max Activating Token Index: 738

Text #15

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.1851. Min Act: -0.1700

Data Index: 7727113 (Open Web Text)

Max Activating Token Index: 479

Text #16

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.1674. Min Act: -0.1700

Data Index: 961833 (Open Web Text)

Max Activating Token Index: 54

Text #17

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.1781. Min Act: -0.1700

Data Index: 5112621 (Open Web Text)

Max Activating Token Index: 114

Text #18

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.1622. Min Act: -0.1700

Data Index: 2542504 (Open Web Text)

Max Activating Token Index: 89

Text #19

Max Range: 3.3392. Min Range: -3.3392

Max Act: 3.1554. Min Act: -0.1700

Data Index: 523842 (Open Web Text)

Max Activating Token Index: 362