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

Dataset: Open Web Text

Neuron 323 in Layer 1

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: 1.9679. Min Range: -1.9679

Max Act: 1.9679. Min Act: -0.1700

Data Index: 2069544 (Open Web Text)

Max Activating Token Index: 637

Text #1

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.9489. Min Act: -0.1700

Data Index: 4303863 (Open Web Text)

Max Activating Token Index: 996

Text #2

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.9373. Min Act: -0.1700

Data Index: 4800652 (Open Web Text)

Max Activating Token Index: 795

Text #3

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.9179. Min Act: -0.1700

Data Index: 258511 (Open Web Text)

Max Activating Token Index: 586

Text #4

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.9304. Min Act: -0.1700

Data Index: 6886004 (Open Web Text)

Max Activating Token Index: 446

Text #5

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.9234. Min Act: -0.1700

Data Index: 5631777 (Open Web Text)

Max Activating Token Index: 502

Text #6

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.9138. Min Act: -0.1700

Data Index: 6769030 (Open Web Text)

Max Activating Token Index: 617

Text #7

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.9005. Min Act: -0.1700

Data Index: 7615191 (Open Web Text)

Max Activating Token Index: 415

Text #8

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.8961. Min Act: -0.1700

Data Index: 7837439 (Open Web Text)

Max Activating Token Index: 656

Text #9

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.9136. Min Act: -0.1700

Data Index: 3124944 (Open Web Text)

Max Activating Token Index: 320

Text #10

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.9022. Min Act: -0.1700

Data Index: 6286001 (Open Web Text)

Max Activating Token Index: 297

Text #11

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.8744. Min Act: -0.1696

Data Index: 4492485 (Open Web Text)

Max Activating Token Index: 988

Text #12

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.8941. Min Act: -0.1700

Data Index: 1565834 (Open Web Text)

Max Activating Token Index: 411

Text #13

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.8950. Min Act: -0.1700

Data Index: 6585322 (Open Web Text)

Max Activating Token Index: 739

Text #14

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.8792. Min Act: -0.1700

Data Index: 3293573 (Open Web Text)

Max Activating Token Index: 561

Text #15

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.8912. Min Act: -0.1698

Data Index: 8103828 (Open Web Text)

Max Activating Token Index: 262

Text #16

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.8741. Min Act: -0.1700

Data Index: 1351039 (Open Web Text)

Max Activating Token Index: 626

Text #17

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.8617. Min Act: -0.1700

Data Index: 3610941 (Open Web Text)

Max Activating Token Index: 592

Text #18

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.8742. Min Act: -0.1700

Data Index: 2851224 (Open Web Text)

Max Activating Token Index: 919

Text #19

Max Range: 1.9679. Min Range: -1.9679

Max Act: 1.8561. Min Act: -0.1700

Data Index: 1643852 (Open Web Text)

Max Activating Token Index: 251