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

Dataset: Open Web Text

Neuron 1902 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: 3.2444. Min Range: -3.2444

Max Act: 3.2444. Min Act: -0.1700

Data Index: 2630614 (Open Web Text)

Max Activating Token Index: 181

Text #1

Max Range: 3.2444. Min Range: -3.2444

Max Act: 3.2075. Min Act: -0.1700

Data Index: 2402798 (Open Web Text)

Max Activating Token Index: 191

Text #2

Max Range: 3.2444. Min Range: -3.2444

Max Act: 3.2038. Min Act: -0.1700

Data Index: 4327556 (Open Web Text)

Max Activating Token Index: 223

Text #3

Max Range: 3.2444. Min Range: -3.2444

Max Act: 3.1508. Min Act: -0.1700

Data Index: 4455332 (Open Web Text)

Max Activating Token Index: 755

Text #4

Max Range: 3.2444. Min Range: -3.2444

Max Act: 3.1343. Min Act: -0.1700

Data Index: 7204695 (Open Web Text)

Max Activating Token Index: 149

Text #5

Max Range: 3.2444. Min Range: -3.2444

Max Act: 3.1388. Min Act: -0.1700

Data Index: 7929602 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.2444. Min Range: -3.2444

Max Act: 3.1142. Min Act: -0.1700

Data Index: 6744827 (Open Web Text)

Max Activating Token Index: 74

Text #7

Max Range: 3.2444. Min Range: -3.2444

Max Act: 3.0895. Min Act: -0.1700

Data Index: 1679845 (Open Web Text)

Max Activating Token Index: 874

Text #8

Max Range: 3.2444. Min Range: -3.2444

Max Act: 3.0963. Min Act: -0.1700

Data Index: 4839718 (Open Web Text)

Max Activating Token Index: 1007

Text #9

Max Range: 3.2444. Min Range: -3.2444

Max Act: 3.1032. Min Act: -0.1700

Data Index: 4738070 (Open Web Text)

Max Activating Token Index: 360

Text #10

Max Range: 3.2444. Min Range: -3.2444

Max Act: 3.1143. Min Act: -0.1700

Data Index: 3813434 (Open Web Text)

Max Activating Token Index: 393

Text #11

Max Range: 3.2444. Min Range: -3.2444

Max Act: 3.1036. Min Act: -0.1700

Data Index: 564756 (Open Web Text)

Max Activating Token Index: 637

Text #12

Max Range: 3.2444. Min Range: -3.2444

Max Act: 3.0727. Min Act: -0.1700

Data Index: 5525615 (Open Web Text)

Max Activating Token Index: 824

Text #13

Max Range: 3.2444. Min Range: -3.2444

Max Act: 3.0972. Min Act: -0.1700

Data Index: 7278369 (Open Web Text)

Max Activating Token Index: 420

Text #14

Max Range: 3.2444. Min Range: -3.2444

Max Act: 3.0822. Min Act: -0.1700

Data Index: 3497628 (Open Web Text)

Max Activating Token Index: 481

Text #15

Max Range: 3.2444. Min Range: -3.2444

Max Act: 3.0846. Min Act: -0.1700

Data Index: 4898103 (Open Web Text)

Max Activating Token Index: 381

Text #16

Max Range: 3.2444. Min Range: -3.2444

Max Act: 3.0786. Min Act: -0.1700

Data Index: 144199 (Open Web Text)

Max Activating Token Index: 592

Text #17

Max Range: 3.2444. Min Range: -3.2444

Max Act: 3.0645. Min Act: -0.1700

Data Index: 5995608 (Open Web Text)

Max Activating Token Index: 550

Text #18

Max Range: 3.2444. Min Range: -3.2444

Max Act: 3.0642. Min Act: -0.1700

Data Index: 5483848 (Open Web Text)

Max Activating Token Index: 164

Text #19

Max Range: 3.2444. Min Range: -3.2444

Max Act: 3.0774. Min Act: -0.1700

Data Index: 6191955 (Open Web Text)

Max Activating Token Index: 542