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

Dataset: Open Web Text

Neuron 116 in Layer 2

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: 3.3850. Min Range: -3.3850

Max Act: 3.3850. Min Act: -0.1700

Data Index: 1195994 (Open Web Text)

Max Activating Token Index: 290

Text #1

Max Range: 3.3850. Min Range: -3.3850

Max Act: 3.3777. Min Act: -0.1700

Data Index: 1440028 (Open Web Text)

Max Activating Token Index: 552

Text #2

Max Range: 3.3850. Min Range: -3.3850

Max Act: 3.3584. Min Act: -0.1700

Data Index: 6124820 (Open Web Text)

Max Activating Token Index: 265

Text #3

Max Range: 3.3850. Min Range: -3.3850

Max Act: 3.3542. Min Act: -0.1700

Data Index: 3547657 (Open Web Text)

Max Activating Token Index: 186

Text #4

Max Range: 3.3850. Min Range: -3.3850

Max Act: 3.3298. Min Act: -0.1700

Data Index: 5197060 (Open Web Text)

Max Activating Token Index: 321

Text #5

Max Range: 3.3850. Min Range: -3.3850

Max Act: 3.3263. Min Act: -0.1700

Data Index: 6546058 (Open Web Text)

Max Activating Token Index: 88

Text #6

Max Range: 3.3850. Min Range: -3.3850

Max Act: 3.3313. Min Act: -0.1700

Data Index: 2036907 (Open Web Text)

Max Activating Token Index: 578

Text #7

Max Range: 3.3850. Min Range: -3.3850

Max Act: 3.3126. Min Act: -0.1700

Data Index: 4149560 (Open Web Text)

Max Activating Token Index: 79

Text #8

Max Range: 3.3850. Min Range: -3.3850

Max Act: 3.3133. Min Act: -0.1700

Data Index: 3169395 (Open Web Text)

Max Activating Token Index: 677

Text #9

Max Range: 3.3850. Min Range: -3.3850

Max Act: 3.3287. Min Act: -0.1700

Data Index: 6360738 (Open Web Text)

Max Activating Token Index: 138

Text #10

Max Range: 3.3850. Min Range: -3.3850

Max Act: 3.3139. Min Act: -0.1700

Data Index: 7734970 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 3.3850. Min Range: -3.3850

Max Act: 3.3113. Min Act: -0.1700

Data Index: 4949316 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.3850. Min Range: -3.3850

Max Act: 3.2739. Min Act: -0.1700

Data Index: 4400164 (Open Web Text)

Max Activating Token Index: 946

Text #13

Max Range: 3.3850. Min Range: -3.3850

Max Act: 3.3010. Min Act: -0.1700

Data Index: 7644521 (Open Web Text)

Max Activating Token Index: 707

Text #14

Max Range: 3.3850. Min Range: -3.3850

Max Act: 3.2792. Min Act: -0.1700

Data Index: 5443586 (Open Web Text)

Max Activating Token Index: 758

Text #15

Max Range: 3.3850. Min Range: -3.3850

Max Act: 3.2800. Min Act: -0.1700

Data Index: 6360724 (Open Web Text)

Max Activating Token Index: 773

Text #16

Max Range: 3.3850. Min Range: -3.3850

Max Act: 3.2834. Min Act: -0.1700

Data Index: 5103533 (Open Web Text)

Max Activating Token Index: 615

Text #17

Max Range: 3.3850. Min Range: -3.3850

Max Act: 3.2644. Min Act: -0.1700

Data Index: 6662146 (Open Web Text)

Max Activating Token Index: 740

Text #18

Max Range: 3.3850. Min Range: -3.3850

Max Act: 3.2659. Min Act: -0.1700

Data Index: 6923524 (Open Web Text)

Max Activating Token Index: 787

Text #19

Max Range: 3.3850. Min Range: -3.3850

Max Act: 3.2799. Min Act: -0.1700

Data Index: 4450837 (Open Web Text)

Max Activating Token Index: 46