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

Dataset: Open Web Text

Neuron 2799 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: 3.8520. Min Range: -3.8520

Max Act: 3.8365. Min Act: -0.1700

Data Index: 5084017 (Open Web Text)

Max Activating Token Index: 593

Text #1

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.8520. Min Act: -0.1700

Data Index: 1321384 (Open Web Text)

Max Activating Token Index: 653

Text #2

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.8171. Min Act: -0.1700

Data Index: 7754722 (Open Web Text)

Max Activating Token Index: 655

Text #3

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.8108. Min Act: -0.1700

Data Index: 3645748 (Open Web Text)

Max Activating Token Index: 650

Text #4

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.8518. Min Act: -0.1700

Data Index: 4916568 (Open Web Text)

Max Activating Token Index: 629

Text #5

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.8459. Min Act: -0.1700

Data Index: 1123174 (Open Web Text)

Max Activating Token Index: 631

Text #6

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.8231. Min Act: -0.1700

Data Index: 1747560 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.7837. Min Act: -0.1700

Data Index: 5671184 (Open Web Text)

Max Activating Token Index: 141

Text #8

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.8041. Min Act: -0.1700

Data Index: 7249006 (Open Web Text)

Max Activating Token Index: 483

Text #9

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.7993. Min Act: -0.1700

Data Index: 7428133 (Open Web Text)

Max Activating Token Index: 630

Text #10

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.8091. Min Act: -0.1700

Data Index: 7649714 (Open Web Text)

Max Activating Token Index: 93

Text #11

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.8063. Min Act: -0.1700

Data Index: 394402 (Open Web Text)

Max Activating Token Index: 486

Text #12

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.7708. Min Act: -0.1700

Data Index: 358503 (Open Web Text)

Max Activating Token Index: 699

Text #13

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.7526. Min Act: -0.1700

Data Index: 3885531 (Open Web Text)

Max Activating Token Index: 439

Text #14

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.7601. Min Act: -0.1700

Data Index: 3885044 (Open Web Text)

Max Activating Token Index: 71

Text #15

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.7652. Min Act: -0.1700

Data Index: 2078633 (Open Web Text)

Max Activating Token Index: 1016

Text #16

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.7871. Min Act: -0.1700

Data Index: 1892393 (Open Web Text)

Max Activating Token Index: 179

Text #17

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.7631. Min Act: -0.1700

Data Index: 3486205 (Open Web Text)

Max Activating Token Index: 730

Text #18

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.7682. Min Act: -0.1700

Data Index: 4916532 (Open Web Text)

Max Activating Token Index: 718

Text #19

Max Range: 3.8520. Min Range: -3.8520

Max Act: 3.7906. Min Act: -0.1700

Data Index: 5133672 (Open Web Text)

Max Activating Token Index: 490