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

Dataset: Open Web Text

Neuron 6 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: 3.4634. Min Range: -3.4634

Max Act: 3.4634. Min Act: -0.1700

Data Index: 5275962 (Open Web Text)

Max Activating Token Index: 567

Text #1

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.4468. Min Act: -0.1700

Data Index: 1751816 (Open Web Text)

Max Activating Token Index: 448

Text #2

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.4114. Min Act: -0.1700

Data Index: 1776487 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.4082. Min Act: -0.1700

Data Index: 7072142 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.4045. Min Act: -0.1700

Data Index: 5419114 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.3973. Min Act: -0.1700

Data Index: 239723 (Open Web Text)

Max Activating Token Index: 23

Text #6

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.3797. Min Act: -0.1700

Data Index: 3990816 (Open Web Text)

Max Activating Token Index: 465

Text #7

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.3735. Min Act: -0.1700

Data Index: 2731230 (Open Web Text)

Max Activating Token Index: 511

Text #8

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.4098. Min Act: -0.1700

Data Index: 1328191 (Open Web Text)

Max Activating Token Index: 746

Text #9

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.3563. Min Act: -0.1700

Data Index: 8144100 (Open Web Text)

Max Activating Token Index: 242

Text #10

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.3387. Min Act: -0.1700

Data Index: 1051632 (Open Web Text)

Max Activating Token Index: 1006

Text #11

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.3438. Min Act: -0.1700

Data Index: 7670172 (Open Web Text)

Max Activating Token Index: 748

Text #12

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.3683. Min Act: -0.1700

Data Index: 1231995 (Open Web Text)

Max Activating Token Index: 771

Text #13

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.3441. Min Act: -0.1700

Data Index: 3645056 (Open Web Text)

Max Activating Token Index: 205

Text #14

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.3340. Min Act: -0.1700

Data Index: 18293 (Open Web Text)

Max Activating Token Index: 605

Text #15

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.3516. Min Act: -0.1700

Data Index: 2817446 (Open Web Text)

Max Activating Token Index: 595

Text #16

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.3465. Min Act: -0.1700

Data Index: 1156707 (Open Web Text)

Max Activating Token Index: 669

Text #17

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.3321. Min Act: -0.1700

Data Index: 431443 (Open Web Text)

Max Activating Token Index: 201

Text #18

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.3528. Min Act: -0.1700

Data Index: 5946374 (Open Web Text)

Max Activating Token Index: 57

Text #19

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.3296. Min Act: -0.1700

Data Index: 3068253 (Open Web Text)

Max Activating Token Index: 26