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

Dataset: Open Web Text

Neuron 1022 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: 1.7939. Min Range: -1.7939

Max Act: 1.7939. Min Act: -0.1700

Data Index: 6577862 (Open Web Text)

Max Activating Token Index: 242

Text #1

Max Range: 1.7939. Min Range: -1.7939

Max Act: 1.7905. Min Act: -0.1700

Data Index: 1342191 (Open Web Text)

Max Activating Token Index: 824

Text #2

Max Range: 1.7939. Min Range: -1.7939

Max Act: 1.7404. Min Act: -0.1696

Data Index: 1476316 (Open Web Text)

Max Activating Token Index: 823

Text #3

Max Range: 1.7939. Min Range: -1.7939

Max Act: 1.7146. Min Act: -0.1694

Data Index: 7791642 (Open Web Text)

Max Activating Token Index: 376

Text #4

Max Range: 1.7939. Min Range: -1.7939

Max Act: 1.6928. Min Act: -0.1699

Data Index: 7010423 (Open Web Text)

Max Activating Token Index: 128

Text #5

Max Range: 1.7939. Min Range: -1.7939

Max Act: 1.6948. Min Act: -0.1700

Data Index: 2372034 (Open Web Text)

Max Activating Token Index: 890

Text #6

Max Range: 1.7939. Min Range: -1.7939

Max Act: 1.6722. Min Act: -0.1700

Data Index: 3355581 (Open Web Text)

Max Activating Token Index: 566

Text #7

Max Range: 1.7939. Min Range: -1.7939

Max Act: 1.6719. Min Act: -0.1692

Data Index: 1136029 (Open Web Text)

Max Activating Token Index: 544

Text #8

Max Range: 1.7939. Min Range: -1.7939

Max Act: 1.6810. Min Act: -0.1700

Data Index: 6876285 (Open Web Text)

Max Activating Token Index: 264

Text #9

Max Range: 1.7939. Min Range: -1.7939

Max Act: 1.6677. Min Act: -0.1700

Data Index: 4601108 (Open Web Text)

Max Activating Token Index: 391

Text #10

Max Range: 1.7939. Min Range: -1.7939

Max Act: 1.6574. Min Act: -0.1699

Data Index: 6978609 (Open Web Text)

Max Activating Token Index: 136

Text #11

Max Range: 1.7939. Min Range: -1.7939

Max Act: 1.6583. Min Act: -0.1700

Data Index: 267414 (Open Web Text)

Max Activating Token Index: 185

Text #12

Max Range: 1.7939. Min Range: -1.7939

Max Act: 1.6555. Min Act: -0.1699

Data Index: 6783755 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 1.7939. Min Range: -1.7939

Max Act: 1.6593. Min Act: -0.1700

Data Index: 2533515 (Open Web Text)

Max Activating Token Index: 433

Text #14

Max Range: 1.7939. Min Range: -1.7939

Max Act: 1.6524. Min Act: -0.1700

Data Index: 6808728 (Open Web Text)

Max Activating Token Index: 560

Text #15

Max Range: 1.7939. Min Range: -1.7939

Max Act: 1.6519. Min Act: -0.1700

Data Index: 7075077 (Open Web Text)

Max Activating Token Index: 709

Text #16

Max Range: 1.7939. Min Range: -1.7939

Max Act: 1.6448. Min Act: -0.1700

Data Index: 8532386 (Open Web Text)

Max Activating Token Index: 509

Text #17

Max Range: 1.7939. Min Range: -1.7939

Max Act: 1.6490. Min Act: -0.1700

Data Index: 270249 (Open Web Text)

Max Activating Token Index: 565

Text #18

Max Range: 1.7939. Min Range: -1.7939

Max Act: 1.6494. Min Act: -0.1700

Data Index: 5415580 (Open Web Text)

Max Activating Token Index: 202

Text #19

Max Range: 1.7939. Min Range: -1.7939

Max Act: 1.6506. Min Act: -0.1700

Data Index: 1920846 (Open Web Text)

Max Activating Token Index: 807