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

Dataset: Open Web Text

Neuron 868 in Layer 5

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: 3.9938. Min Range: -3.9938

Max Act: 3.9938. Min Act: -0.1700

Data Index: 5040253 (Open Web Text)

Max Activating Token Index: 416

Text #1

Max Range: 3.9938. Min Range: -3.9938

Max Act: 3.9808. Min Act: -0.1700

Data Index: 4638103 (Open Web Text)

Max Activating Token Index: 485

Text #2

Max Range: 3.9938. Min Range: -3.9938

Max Act: 3.8962. Min Act: -0.1700

Data Index: 1352792 (Open Web Text)

Max Activating Token Index: 865

Text #3

Max Range: 3.9938. Min Range: -3.9938

Max Act: 3.8243. Min Act: -0.1700

Data Index: 6292149 (Open Web Text)

Max Activating Token Index: 582

Text #4

Max Range: 3.9938. Min Range: -3.9938

Max Act: 3.7643. Min Act: -0.1700

Data Index: 1352793 (Open Web Text)

Max Activating Token Index: 585

Text #5

Max Range: 3.9938. Min Range: -3.9938

Max Act: 3.7261. Min Act: -0.1700

Data Index: 2672694 (Open Web Text)

Max Activating Token Index: 757

Text #6

Max Range: 3.9938. Min Range: -3.9938

Max Act: 3.7486. Min Act: -0.1700

Data Index: 6103980 (Open Web Text)

Max Activating Token Index: 425

Text #7

Max Range: 3.9938. Min Range: -3.9938

Max Act: 3.6801. Min Act: -0.1700

Data Index: 4638101 (Open Web Text)

Max Activating Token Index: 578

Text #8

Max Range: 3.9938. Min Range: -3.9938

Max Act: 3.7224. Min Act: -0.1700

Data Index: 1877518 (Open Web Text)

Max Activating Token Index: 824

Text #9

Max Range: 3.9938. Min Range: -3.9938

Max Act: 3.6970. Min Act: -0.1700

Data Index: 4638102 (Open Web Text)

Max Activating Token Index: 555

Text #10

Max Range: 3.9938. Min Range: -3.9938

Max Act: 3.6932. Min Act: -0.1700

Data Index: 8635925 (Open Web Text)

Max Activating Token Index: 600

Text #11

Max Range: 3.9938. Min Range: -3.9938

Max Act: 3.6690. Min Act: -0.1700

Data Index: 3391585 (Open Web Text)

Max Activating Token Index: 405

Text #12

Max Range: 3.9938. Min Range: -3.9938

Max Act: 3.6531. Min Act: -0.1700

Data Index: 4918014 (Open Web Text)

Max Activating Token Index: 352

Text #13

Max Range: 3.9938. Min Range: -3.9938

Max Act: 3.6396. Min Act: -0.1700

Data Index: 7713720 (Open Web Text)

Max Activating Token Index: 579

Text #14

Max Range: 3.9938. Min Range: -3.9938

Max Act: 3.5877. Min Act: -0.1700

Data Index: 5056532 (Open Web Text)

Max Activating Token Index: 647

Text #15

Max Range: 3.9938. Min Range: -3.9938

Max Act: 3.6046. Min Act: -0.1700

Data Index: 7496949 (Open Web Text)

Max Activating Token Index: 670

Text #16

Max Range: 3.9938. Min Range: -3.9938

Max Act: 3.5908. Min Act: -0.1700

Data Index: 105136 (Open Web Text)

Max Activating Token Index: 521

Text #17

Max Range: 3.9938. Min Range: -3.9938

Max Act: 3.6335. Min Act: -0.1700

Data Index: 2445147 (Open Web Text)

Max Activating Token Index: 272

Text #18

Max Range: 3.9938. Min Range: -3.9938

Max Act: 3.5706. Min Act: -0.1700

Data Index: 8503899 (Open Web Text)

Max Activating Token Index: 599

Text #19

Max Range: 3.9938. Min Range: -3.9938

Max Act: 3.5837. Min Act: -0.1700

Data Index: 3183098 (Open Web Text)

Max Activating Token Index: 661