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

Dataset: Open Web Text

Neuron 347 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: 3.0516. Min Range: -3.0516

Max Act: 3.0370. Min Act: -0.1700

Data Index: 1354475 (Open Web Text)

Max Activating Token Index: 166

Text #1

Max Range: 3.0516. Min Range: -3.0516

Max Act: 3.0268. Min Act: -0.1700

Data Index: 8234252 (Open Web Text)

Max Activating Token Index: 33

Text #2

Max Range: 3.0516. Min Range: -3.0516

Max Act: 3.0516. Min Act: -0.1700

Data Index: 728332 (Open Web Text)

Max Activating Token Index: 172

Text #3

Max Range: 3.0516. Min Range: -3.0516

Max Act: 3.0477. Min Act: -0.1700

Data Index: 811163 (Open Web Text)

Max Activating Token Index: 297

Text #4

Max Range: 3.0516. Min Range: -3.0516

Max Act: 3.0022. Min Act: -0.1700

Data Index: 8655739 (Open Web Text)

Max Activating Token Index: 949

Text #5

Max Range: 3.0516. Min Range: -3.0516

Max Act: 2.9868. Min Act: -0.1700

Data Index: 8655751 (Open Web Text)

Max Activating Token Index: 260

Text #6

Max Range: 3.0516. Min Range: -3.0516

Max Act: 2.9686. Min Act: -0.1700

Data Index: 2093512 (Open Web Text)

Max Activating Token Index: 705

Text #7

Max Range: 3.0516. Min Range: -3.0516

Max Act: 2.9774. Min Act: -0.1700

Data Index: 2724477 (Open Web Text)

Max Activating Token Index: 226

Text #8

Max Range: 3.0516. Min Range: -3.0516

Max Act: 2.9678. Min Act: -0.1700

Data Index: 5012313 (Open Web Text)

Max Activating Token Index: 437

Text #9

Max Range: 3.0516. Min Range: -3.0516

Max Act: 2.9676. Min Act: -0.1700

Data Index: 6371182 (Open Web Text)

Max Activating Token Index: 115

Text #10

Max Range: 3.0516. Min Range: -3.0516

Max Act: 2.9161. Min Act: -0.1700

Data Index: 5291490 (Open Web Text)

Max Activating Token Index: 434

Text #11

Max Range: 3.0516. Min Range: -3.0516

Max Act: 2.9194. Min Act: -0.1700

Data Index: 464202 (Open Web Text)

Max Activating Token Index: 371

Text #12

Max Range: 3.0516. Min Range: -3.0516

Max Act: 2.9093. Min Act: -0.1700

Data Index: 7413333 (Open Web Text)

Max Activating Token Index: 290

Text #13

Max Range: 3.0516. Min Range: -3.0516

Max Act: 2.9242. Min Act: -0.1700

Data Index: 3299003 (Open Web Text)

Max Activating Token Index: 451

Text #14

Max Range: 3.0516. Min Range: -3.0516

Max Act: 2.9050. Min Act: -0.1700

Data Index: 1672321 (Open Web Text)

Max Activating Token Index: 171

Text #15

Max Range: 3.0516. Min Range: -3.0516

Max Act: 2.8846. Min Act: -0.1700

Data Index: 5196074 (Open Web Text)

Max Activating Token Index: 843

Text #16

Max Range: 3.0516. Min Range: -3.0516

Max Act: 2.8953. Min Act: -0.1700

Data Index: 5855831 (Open Web Text)

Max Activating Token Index: 603

Text #17

Max Range: 3.0516. Min Range: -3.0516

Max Act: 2.9164. Min Act: -0.1700

Data Index: 991873 (Open Web Text)

Max Activating Token Index: 708

Text #18

Max Range: 3.0516. Min Range: -3.0516

Max Act: 2.8835. Min Act: -0.1700

Data Index: 5622220 (Open Web Text)

Max Activating Token Index: 669

Text #19

Max Range: 3.0516. Min Range: -3.0516

Max Act: 2.8993. Min Act: -0.1700

Data Index: 7410620 (Open Web Text)

Max Activating Token Index: 940