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

Dataset: Open Web Text

Neuron 2664 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: 3.7097. Min Range: -3.7097

Max Act: 3.7097. Min Act: -0.1700

Data Index: 1651616 (Open Web Text)

Max Activating Token Index: 603

Text #1

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.6293. Min Act: -0.1700

Data Index: 943356 (Open Web Text)

Max Activating Token Index: 652

Text #2

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.6723. Min Act: -0.1700

Data Index: 2656274 (Open Web Text)

Max Activating Token Index: 283

Text #3

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.6225. Min Act: -0.1700

Data Index: 1303397 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.5812. Min Act: -0.1700

Data Index: 7708094 (Open Web Text)

Max Activating Token Index: 702

Text #5

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.6192. Min Act: -0.1700

Data Index: 5372604 (Open Web Text)

Max Activating Token Index: 438

Text #6

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.5602. Min Act: -0.1700

Data Index: 5859080 (Open Web Text)

Max Activating Token Index: 595

Text #7

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.5626. Min Act: -0.1700

Data Index: 476164 (Open Web Text)

Max Activating Token Index: 505

Text #8

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.5122. Min Act: -0.1700

Data Index: 6551639 (Open Web Text)

Max Activating Token Index: 111

Text #9

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.5221. Min Act: -0.1700

Data Index: 4856635 (Open Web Text)

Max Activating Token Index: 381

Text #10

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.5161. Min Act: -0.1700

Data Index: 4958506 (Open Web Text)

Max Activating Token Index: 531

Text #11

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.5235. Min Act: -0.1700

Data Index: 5368961 (Open Web Text)

Max Activating Token Index: 575

Text #12

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.5270. Min Act: -0.1700

Data Index: 7948146 (Open Web Text)

Max Activating Token Index: 598

Text #13

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.4900. Min Act: -0.1700

Data Index: 6755924 (Open Web Text)

Max Activating Token Index: 732

Text #14

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.4886. Min Act: -0.1700

Data Index: 6780395 (Open Web Text)

Max Activating Token Index: 109

Text #15

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.4319. Min Act: -0.1700

Data Index: 7680890 (Open Web Text)

Max Activating Token Index: 941

Text #16

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.4347. Min Act: -0.1700

Data Index: 1035623 (Open Web Text)

Max Activating Token Index: 383

Text #17

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.4589. Min Act: -0.1700

Data Index: 6725970 (Open Web Text)

Max Activating Token Index: 688

Text #18

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.4955. Min Act: -0.1700

Data Index: 7481612 (Open Web Text)

Max Activating Token Index: 755

Text #19

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.4853. Min Act: -0.1700

Data Index: 5180381 (Open Web Text)

Max Activating Token Index: 446