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

Dataset: Open Web Text

Neuron 1455 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: 4.9153. Min Range: -4.9153

Max Act: 4.9153. Min Act: -0.1700

Data Index: 7365211 (Open Web Text)

Max Activating Token Index: 516

Text #1

Max Range: 4.9153. Min Range: -4.9153

Max Act: 4.8100. Min Act: -0.1700

Data Index: 3150535 (Open Web Text)

Max Activating Token Index: 659

Text #2

Max Range: 4.9153. Min Range: -4.9153

Max Act: 4.7801. Min Act: -0.1700

Data Index: 6365829 (Open Web Text)

Max Activating Token Index: 1000

Text #3

Max Range: 4.9153. Min Range: -4.9153

Max Act: 4.7680. Min Act: -0.1700

Data Index: 8205948 (Open Web Text)

Max Activating Token Index: 779

Text #4

Max Range: 4.9153. Min Range: -4.9153

Max Act: 4.7380. Min Act: -0.1700

Data Index: 2837724 (Open Web Text)

Max Activating Token Index: 830

Text #5

Max Range: 4.9153. Min Range: -4.9153

Max Act: 4.7438. Min Act: -0.1700

Data Index: 6307393 (Open Web Text)

Max Activating Token Index: 983

Text #6

Max Range: 4.9153. Min Range: -4.9153

Max Act: 4.6802. Min Act: -0.1700

Data Index: 5073864 (Open Web Text)

Max Activating Token Index: 504

Text #7

Max Range: 4.9153. Min Range: -4.9153

Max Act: 4.6778. Min Act: -0.1700

Data Index: 783664 (Open Web Text)

Max Activating Token Index: 946

Text #8

Max Range: 4.9153. Min Range: -4.9153

Max Act: 4.6671. Min Act: -0.1700

Data Index: 6749303 (Open Web Text)

Max Activating Token Index: 961

Text #9

Max Range: 4.9153. Min Range: -4.9153

Max Act: 4.6744. Min Act: -0.1700

Data Index: 6301360 (Open Web Text)

Max Activating Token Index: 884

Text #10

Max Range: 4.9153. Min Range: -4.9153

Max Act: 4.7140. Min Act: -0.1700

Data Index: 1065410 (Open Web Text)

Max Activating Token Index: 991

Text #11

Max Range: 4.9153. Min Range: -4.9153

Max Act: 4.6672. Min Act: -0.1700

Data Index: 2677505 (Open Web Text)

Max Activating Token Index: 928

Text #12

Max Range: 4.9153. Min Range: -4.9153

Max Act: 4.7021. Min Act: -0.1700

Data Index: 7142823 (Open Web Text)

Max Activating Token Index: 961

Text #13

Max Range: 4.9153. Min Range: -4.9153

Max Act: 4.6578. Min Act: -0.1700

Data Index: 7567946 (Open Web Text)

Max Activating Token Index: 551

Text #14

Max Range: 4.9153. Min Range: -4.9153

Max Act: 4.6645. Min Act: -0.1700

Data Index: 1006873 (Open Web Text)

Max Activating Token Index: 844

Text #15

Max Range: 4.9153. Min Range: -4.9153

Max Act: 4.6744. Min Act: -0.1700

Data Index: 2863394 (Open Web Text)

Max Activating Token Index: 519

Text #16

Max Range: 4.9153. Min Range: -4.9153

Max Act: 4.6736. Min Act: -0.1700

Data Index: 8325587 (Open Web Text)

Max Activating Token Index: 923

Text #17

Max Range: 4.9153. Min Range: -4.9153

Max Act: 4.6878. Min Act: -0.1700

Data Index: 3687611 (Open Web Text)

Max Activating Token Index: 491

Text #18

Max Range: 4.9153. Min Range: -4.9153

Max Act: 4.6241. Min Act: -0.1700

Data Index: 3065640 (Open Web Text)

Max Activating Token Index: 833

Text #19

Max Range: 4.9153. Min Range: -4.9153

Max Act: 4.6126. Min Act: -0.1700

Data Index: 7388505 (Open Web Text)

Max Activating Token Index: 770