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

Dataset: Open Web Text

Neuron 2838 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: 5.1823. Min Range: -5.1823

Max Act: 5.1823. Min Act: -0.1700

Data Index: 5646322 (Open Web Text)

Max Activating Token Index: 557

Text #1

Max Range: 5.1823. Min Range: -5.1823

Max Act: 5.0966. Min Act: -0.1700

Data Index: 4463051 (Open Web Text)

Max Activating Token Index: 573

Text #2

Max Range: 5.1823. Min Range: -5.1823

Max Act: 5.1610. Min Act: -0.1700

Data Index: 5646317 (Open Web Text)

Max Activating Token Index: 153

Text #3

Max Range: 5.1823. Min Range: -5.1823

Max Act: 5.1251. Min Act: -0.1700

Data Index: 5994775 (Open Web Text)

Max Activating Token Index: 187

Text #4

Max Range: 5.1823. Min Range: -5.1823

Max Act: 5.0641. Min Act: -0.1700

Data Index: 4966644 (Open Web Text)

Max Activating Token Index: 569

Text #5

Max Range: 5.1823. Min Range: -5.1823

Max Act: 5.1192. Min Act: -0.1700

Data Index: 1149076 (Open Web Text)

Max Activating Token Index: 489

Text #6

Max Range: 5.1823. Min Range: -5.1823

Max Act: 4.8920. Min Act: -0.1700

Data Index: 2587683 (Open Web Text)

Max Activating Token Index: 530

Text #7

Max Range: 5.1823. Min Range: -5.1823

Max Act: 4.9249. Min Act: -0.1700

Data Index: 4653165 (Open Web Text)

Max Activating Token Index: 557

Text #8

Max Range: 5.1823. Min Range: -5.1823

Max Act: 4.8707. Min Act: -0.1700

Data Index: 3898979 (Open Web Text)

Max Activating Token Index: 1007

Text #9

Max Range: 5.1823. Min Range: -5.1823

Max Act: 4.8762. Min Act: -0.1700

Data Index: 529471 (Open Web Text)

Max Activating Token Index: 565

Text #10

Max Range: 5.1823. Min Range: -5.1823

Max Act: 4.8865. Min Act: -0.1700

Data Index: 8350295 (Open Web Text)

Max Activating Token Index: 352

Text #11

Max Range: 5.1823. Min Range: -5.1823

Max Act: 4.8293. Min Act: -0.1700

Data Index: 6888011 (Open Web Text)

Max Activating Token Index: 960

Text #12

Max Range: 5.1823. Min Range: -5.1823

Max Act: 4.8557. Min Act: -0.1700

Data Index: 7509505 (Open Web Text)

Max Activating Token Index: 200

Text #13

Max Range: 5.1823. Min Range: -5.1823

Max Act: 4.8303. Min Act: -0.1700

Data Index: 5292035 (Open Web Text)

Max Activating Token Index: 403

Text #14

Max Range: 5.1823. Min Range: -5.1823

Max Act: 4.7689. Min Act: -0.1700

Data Index: 7488228 (Open Web Text)

Max Activating Token Index: 578

Text #15

Max Range: 5.1823. Min Range: -5.1823

Max Act: 4.8136. Min Act: -0.1700

Data Index: 4852933 (Open Web Text)

Max Activating Token Index: 413

Text #16

Max Range: 5.1823. Min Range: -5.1823

Max Act: 4.7945. Min Act: -0.1700

Data Index: 6330570 (Open Web Text)

Max Activating Token Index: 958

Text #17

Max Range: 5.1823. Min Range: -5.1823

Max Act: 4.7686. Min Act: -0.1700

Data Index: 3339512 (Open Web Text)

Max Activating Token Index: 758

Text #18

Max Range: 5.1823. Min Range: -5.1823

Max Act: 4.7766. Min Act: -0.1700

Data Index: 3681731 (Open Web Text)

Max Activating Token Index: 562

Text #19

Max Range: 5.1823. Min Range: -5.1823

Max Act: 4.7297. Min Act: -0.1700

Data Index: 5867037 (Open Web Text)

Max Activating Token Index: 1000