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

Dataset: Open Web Text

Neuron 2377 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: 4.3267. Min Range: -4.3267

Max Act: 4.3267. Min Act: -0.1700

Data Index: 4848189 (Open Web Text)

Max Activating Token Index: 393

Text #1

Max Range: 4.3267. Min Range: -4.3267

Max Act: 4.2933. Min Act: -0.1700

Data Index: 6435813 (Open Web Text)

Max Activating Token Index: 342

Text #2

Max Range: 4.3267. Min Range: -4.3267

Max Act: 4.2608. Min Act: -0.1700

Data Index: 3614033 (Open Web Text)

Max Activating Token Index: 240

Text #3

Max Range: 4.3267. Min Range: -4.3267

Max Act: 4.2656. Min Act: -0.1700

Data Index: 6519873 (Open Web Text)

Max Activating Token Index: 273

Text #4

Max Range: 4.3267. Min Range: -4.3267

Max Act: 4.2131. Min Act: -0.1700

Data Index: 2670208 (Open Web Text)

Max Activating Token Index: 641

Text #5

Max Range: 4.3267. Min Range: -4.3267

Max Act: 4.2011. Min Act: -0.1700

Data Index: 3275258 (Open Web Text)

Max Activating Token Index: 92

Text #6

Max Range: 4.3267. Min Range: -4.3267

Max Act: 4.2123. Min Act: -0.1700

Data Index: 3951646 (Open Web Text)

Max Activating Token Index: 787

Text #7

Max Range: 4.3267. Min Range: -4.3267

Max Act: 4.2063. Min Act: -0.1700

Data Index: 7855351 (Open Web Text)

Max Activating Token Index: 856

Text #8

Max Range: 4.3267. Min Range: -4.3267

Max Act: 4.2249. Min Act: -0.1700

Data Index: 6657698 (Open Web Text)

Max Activating Token Index: 133

Text #9

Max Range: 4.3267. Min Range: -4.3267

Max Act: 4.2186. Min Act: -0.1700

Data Index: 652439 (Open Web Text)

Max Activating Token Index: 877

Text #10

Max Range: 4.3267. Min Range: -4.3267

Max Act: 4.1733. Min Act: -0.1700

Data Index: 5608582 (Open Web Text)

Max Activating Token Index: 561

Text #11

Max Range: 4.3267. Min Range: -4.3267

Max Act: 4.1789. Min Act: -0.1700

Data Index: 6602994 (Open Web Text)

Max Activating Token Index: 411

Text #12

Max Range: 4.3267. Min Range: -4.3267

Max Act: 4.1500. Min Act: -0.1700

Data Index: 374667 (Open Web Text)

Max Activating Token Index: 186

Text #13

Max Range: 4.3267. Min Range: -4.3267

Max Act: 4.1670. Min Act: -0.1700

Data Index: 3514843 (Open Web Text)

Max Activating Token Index: 863

Text #14

Max Range: 4.3267. Min Range: -4.3267

Max Act: 4.1645. Min Act: -0.1700

Data Index: 5281287 (Open Web Text)

Max Activating Token Index: 519

Text #15

Max Range: 4.3267. Min Range: -4.3267

Max Act: 4.1086. Min Act: -0.1700

Data Index: 5848713 (Open Web Text)

Max Activating Token Index: 161

Text #16

Max Range: 4.3267. Min Range: -4.3267

Max Act: 4.1181. Min Act: -0.1700

Data Index: 2006885 (Open Web Text)

Max Activating Token Index: 314

Text #17

Max Range: 4.3267. Min Range: -4.3267

Max Act: 4.1292. Min Act: -0.1700

Data Index: 2775755 (Open Web Text)

Max Activating Token Index: 238

Text #18

Max Range: 4.3267. Min Range: -4.3267

Max Act: 4.1029. Min Act: -0.1700

Data Index: 2135727 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.3267. Min Range: -4.3267

Max Act: 4.1071. Min Act: -0.1700

Data Index: 6385400 (Open Web Text)

Max Activating Token Index: 903