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

Dataset: Open Web Text

Neuron 2162 in Layer 6

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: 5.4898. Min Range: -5.4898

Max Act: 5.4617. Min Act: -0.1700

Data Index: 1244978 (Open Web Text)

Max Activating Token Index: 774

Text #1

Max Range: 5.4898. Min Range: -5.4898

Max Act: 5.4898. Min Act: -0.1700

Data Index: 6442844 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 5.4898. Min Range: -5.4898

Max Act: 5.4496. Min Act: -0.1700

Data Index: 1173904 (Open Web Text)

Max Activating Token Index: 373

Text #3

Max Range: 5.4898. Min Range: -5.4898

Max Act: 5.4606. Min Act: -0.1700

Data Index: 6463695 (Open Web Text)

Max Activating Token Index: 901

Text #4

Max Range: 5.4898. Min Range: -5.4898

Max Act: 5.4631. Min Act: -0.1700

Data Index: 2560105 (Open Web Text)

Max Activating Token Index: 895

Text #5

Max Range: 5.4898. Min Range: -5.4898

Max Act: 5.4288. Min Act: -0.1700

Data Index: 7923907 (Open Web Text)

Max Activating Token Index: 924

Text #6

Max Range: 5.4898. Min Range: -5.4898

Max Act: 5.3495. Min Act: -0.1700

Data Index: 7923905 (Open Web Text)

Max Activating Token Index: 953

Text #7

Max Range: 5.4898. Min Range: -5.4898

Max Act: 5.3720. Min Act: -0.1700

Data Index: 7923906 (Open Web Text)

Max Activating Token Index: 733

Text #8

Max Range: 5.4898. Min Range: -5.4898

Max Act: 5.3464. Min Act: -0.1700

Data Index: 4650251 (Open Web Text)

Max Activating Token Index: 780

Text #9

Max Range: 5.4898. Min Range: -5.4898

Max Act: 5.3345. Min Act: -0.1700

Data Index: 8517192 (Open Web Text)

Max Activating Token Index: 1005

Text #10

Max Range: 5.4898. Min Range: -5.4898

Max Act: 5.2425. Min Act: -0.1700

Data Index: 2429995 (Open Web Text)

Max Activating Token Index: 423

Text #11

Max Range: 5.4898. Min Range: -5.4898

Max Act: 5.2125. Min Act: -0.1700

Data Index: 6339969 (Open Web Text)

Max Activating Token Index: 858

Text #12

Max Range: 5.4898. Min Range: -5.4898

Max Act: 5.1946. Min Act: -0.1700

Data Index: 7168671 (Open Web Text)

Max Activating Token Index: 805

Text #13

Max Range: 5.4898. Min Range: -5.4898

Max Act: 5.2131. Min Act: -0.1700

Data Index: 5157292 (Open Web Text)

Max Activating Token Index: 550

Text #14

Max Range: 5.4898. Min Range: -5.4898

Max Act: 5.1963. Min Act: -0.1700

Data Index: 4275083 (Open Web Text)

Max Activating Token Index: 495

Text #15

Max Range: 5.4898. Min Range: -5.4898

Max Act: 5.1549. Min Act: -0.1700

Data Index: 4650252 (Open Web Text)

Max Activating Token Index: 518

Text #16

Max Range: 5.4898. Min Range: -5.4898

Max Act: 5.1124. Min Act: -0.1700

Data Index: 7083149 (Open Web Text)

Max Activating Token Index: 645

Text #17

Max Range: 5.4898. Min Range: -5.4898

Max Act: 5.1638. Min Act: -0.1700

Data Index: 4911618 (Open Web Text)

Max Activating Token Index: 276

Text #18

Max Range: 5.4898. Min Range: -5.4898

Max Act: 5.1553. Min Act: -0.1700

Data Index: 7168673 (Open Web Text)

Max Activating Token Index: 799

Text #19

Max Range: 5.4898. Min Range: -5.4898

Max Act: 5.0897. Min Act: -0.1700

Data Index: 1244979 (Open Web Text)

Max Activating Token Index: 217