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

Dataset: Open Web Text

Neuron 2422 in Layer 3

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: 3.4511. Min Range: -3.4511

Max Act: 3.4511. Min Act: -0.1700

Data Index: 7439324 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 3.4511. Min Range: -3.4511

Max Act: 3.4355. Min Act: -0.1700

Data Index: 5555325 (Open Web Text)

Max Activating Token Index: 413

Text #2

Max Range: 3.4511. Min Range: -3.4511

Max Act: 3.4033. Min Act: -0.1700

Data Index: 1933750 (Open Web Text)

Max Activating Token Index: 27

Text #3

Max Range: 3.4511. Min Range: -3.4511

Max Act: 3.4432. Min Act: -0.1700

Data Index: 1586466 (Open Web Text)

Max Activating Token Index: 403

Text #4

Max Range: 3.4511. Min Range: -3.4511

Max Act: 3.4015. Min Act: -0.1700

Data Index: 4543002 (Open Web Text)

Max Activating Token Index: 21

Text #5

Max Range: 3.4511. Min Range: -3.4511

Max Act: 3.3569. Min Act: -0.1700

Data Index: 8780726 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.4511. Min Range: -3.4511

Max Act: 3.3554. Min Act: -0.1700

Data Index: 7703254 (Open Web Text)

Max Activating Token Index: 1007

Text #7

Max Range: 3.4511. Min Range: -3.4511

Max Act: 3.3336. Min Act: -0.1700

Data Index: 3012825 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 3.4511. Min Range: -3.4511

Max Act: 3.3411. Min Act: -0.1700

Data Index: 1249575 (Open Web Text)

Max Activating Token Index: 920

Text #9

Max Range: 3.4511. Min Range: -3.4511

Max Act: 3.3174. Min Act: -0.1700

Data Index: 6179537 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 3.4511. Min Range: -3.4511

Max Act: 3.3119. Min Act: -0.1700

Data Index: 5194577 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.4511. Min Range: -3.4511

Max Act: 3.3049. Min Act: -0.1700

Data Index: 2374770 (Open Web Text)

Max Activating Token Index: 17

Text #12

Max Range: 3.4511. Min Range: -3.4511

Max Act: 3.3133. Min Act: -0.1700

Data Index: 6418556 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 3.4511. Min Range: -3.4511

Max Act: 3.2750. Min Act: -0.1700

Data Index: 7708355 (Open Web Text)

Max Activating Token Index: 605

Text #14

Max Range: 3.4511. Min Range: -3.4511

Max Act: 3.2959. Min Act: -0.1700

Data Index: 436395 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.4511. Min Range: -3.4511

Max Act: 3.3054. Min Act: -0.1700

Data Index: 4082217 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 3.4511. Min Range: -3.4511

Max Act: 3.2887. Min Act: -0.1700

Data Index: 8015831 (Open Web Text)

Max Activating Token Index: 110

Text #17

Max Range: 3.4511. Min Range: -3.4511

Max Act: 3.2781. Min Act: -0.1700

Data Index: 7020861 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 3.4511. Min Range: -3.4511

Max Act: 3.2881. Min Act: -0.1700

Data Index: 7301429 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 3.4511. Min Range: -3.4511

Max Act: 3.3032. Min Act: -0.1700

Data Index: 6930777 (Open Web Text)

Max Activating Token Index: 40