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

Dataset: Open Web Text

Neuron 656 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: 3.7030. Min Range: -3.7030

Max Act: 3.7014. Min Act: -0.1700

Data Index: 3206079 (Open Web Text)

Max Activating Token Index: 808

Text #1

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.7030. Min Act: -0.1700

Data Index: 6084894 (Open Web Text)

Max Activating Token Index: 485

Text #2

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.6808. Min Act: -0.1700

Data Index: 5510997 (Open Web Text)

Max Activating Token Index: 430

Text #3

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.6557. Min Act: -0.1700

Data Index: 6328436 (Open Web Text)

Max Activating Token Index: 566

Text #4

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.6241. Min Act: -0.1700

Data Index: 1610083 (Open Web Text)

Max Activating Token Index: 447

Text #5

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.5645. Min Act: -0.1700

Data Index: 1876275 (Open Web Text)

Max Activating Token Index: 618

Text #6

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.5390. Min Act: -0.1700

Data Index: 5770634 (Open Web Text)

Max Activating Token Index: 162

Text #7

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.5520. Min Act: -0.1700

Data Index: 500975 (Open Web Text)

Max Activating Token Index: 468

Text #8

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.5066. Min Act: -0.1700

Data Index: 7093524 (Open Web Text)

Max Activating Token Index: 423

Text #9

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.5381. Min Act: -0.1700

Data Index: 5392649 (Open Web Text)

Max Activating Token Index: 454

Text #10

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.5359. Min Act: -0.1700

Data Index: 5096110 (Open Web Text)

Max Activating Token Index: 662

Text #11

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.5166. Min Act: -0.1700

Data Index: 5679461 (Open Web Text)

Max Activating Token Index: 90

Text #12

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.5076. Min Act: -0.1700

Data Index: 1267822 (Open Web Text)

Max Activating Token Index: 632

Text #13

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.5001. Min Act: -0.1700

Data Index: 964417 (Open Web Text)

Max Activating Token Index: 320

Text #14

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.4945. Min Act: -0.1700

Data Index: 1833710 (Open Web Text)

Max Activating Token Index: 993

Text #15

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.4928. Min Act: -0.1700

Data Index: 5968695 (Open Web Text)

Max Activating Token Index: 990

Text #16

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.4763. Min Act: -0.1700

Data Index: 370794 (Open Web Text)

Max Activating Token Index: 43

Text #17

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.5112. Min Act: -0.1700

Data Index: 1655092 (Open Web Text)

Max Activating Token Index: 765

Text #18

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.4911. Min Act: -0.1700

Data Index: 4194111 (Open Web Text)

Max Activating Token Index: 494

Text #19

Max Range: 3.7030. Min Range: -3.7030

Max Act: 3.5014. Min Act: -0.1700

Data Index: 3164688 (Open Web Text)

Max Activating Token Index: 325