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

Dataset: Open Web Text

Neuron 3008 in Layer 3

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: 4.5107. Min Range: -4.5107

Max Act: 4.5107. Min Act: -0.1700

Data Index: 1070600 (Open Web Text)

Max Activating Token Index: 934

Text #1

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.3556. Min Act: -0.1700

Data Index: 2412404 (Open Web Text)

Max Activating Token Index: 363

Text #2

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.3359. Min Act: -0.1700

Data Index: 7149982 (Open Web Text)

Max Activating Token Index: 671

Text #3

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.3029. Min Act: -0.1700

Data Index: 2756061 (Open Web Text)

Max Activating Token Index: 237

Text #4

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.2368. Min Act: -0.1700

Data Index: 6054205 (Open Web Text)

Max Activating Token Index: 312

Text #5

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.2386. Min Act: -0.1700

Data Index: 2111452 (Open Web Text)

Max Activating Token Index: 987

Text #6

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.2552. Min Act: -0.1700

Data Index: 6373296 (Open Web Text)

Max Activating Token Index: 831

Text #7

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.2446. Min Act: -0.1700

Data Index: 6448355 (Open Web Text)

Max Activating Token Index: 49

Text #8

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.2023. Min Act: -0.1700

Data Index: 8679133 (Open Web Text)

Max Activating Token Index: 469

Text #9

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.1979. Min Act: -0.1700

Data Index: 5044268 (Open Web Text)

Max Activating Token Index: 678

Text #10

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.1744. Min Act: -0.1700

Data Index: 4024261 (Open Web Text)

Max Activating Token Index: 202

Text #11

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.1608. Min Act: -0.1700

Data Index: 3639303 (Open Web Text)

Max Activating Token Index: 483

Text #12

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.1980. Min Act: -0.1700

Data Index: 5275847 (Open Web Text)

Max Activating Token Index: 104

Text #13

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.2078. Min Act: -0.1700

Data Index: 8451063 (Open Web Text)

Max Activating Token Index: 392

Text #14

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.2017. Min Act: -0.1700

Data Index: 8167167 (Open Web Text)

Max Activating Token Index: 202

Text #15

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.1486. Min Act: -0.1700

Data Index: 3281544 (Open Web Text)

Max Activating Token Index: 91

Text #16

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.1320. Min Act: -0.1700

Data Index: 7868180 (Open Web Text)

Max Activating Token Index: 110

Text #17

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.1516. Min Act: -0.1700

Data Index: 2966248 (Open Web Text)

Max Activating Token Index: 292

Text #18

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.1403. Min Act: -0.1700

Data Index: 2667402 (Open Web Text)

Max Activating Token Index: 76

Text #19

Max Range: 4.5107. Min Range: -4.5107

Max Act: 4.1914. Min Act: -0.1700

Data Index: 4211021 (Open Web Text)

Max Activating Token Index: 178