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

Dataset: Open Web Text

Neuron 477 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: 3.7825. Min Range: -3.7825

Max Act: 3.7815. Min Act: -0.1700

Data Index: 1358159 (Open Web Text)

Max Activating Token Index: 811

Text #1

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.7825. Min Act: -0.1700

Data Index: 8462537 (Open Web Text)

Max Activating Token Index: 828

Text #2

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.7142. Min Act: -0.1700

Data Index: 6261644 (Open Web Text)

Max Activating Token Index: 895

Text #3

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.7621. Min Act: -0.1700

Data Index: 6261646 (Open Web Text)

Max Activating Token Index: 1017

Text #4

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.6913. Min Act: -0.1700

Data Index: 6261632 (Open Web Text)

Max Activating Token Index: 912

Text #5

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.7014. Min Act: -0.1700

Data Index: 4830315 (Open Web Text)

Max Activating Token Index: 589

Text #6

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.6661. Min Act: -0.1700

Data Index: 5092289 (Open Web Text)

Max Activating Token Index: 918

Text #7

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.6342. Min Act: -0.1700

Data Index: 8555868 (Open Web Text)

Max Activating Token Index: 881

Text #8

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.6163. Min Act: -0.1700

Data Index: 1427638 (Open Web Text)

Max Activating Token Index: 987

Text #9

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5696. Min Act: -0.1700

Data Index: 309981 (Open Web Text)

Max Activating Token Index: 929

Text #10

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5808. Min Act: -0.1700

Data Index: 6264638 (Open Web Text)

Max Activating Token Index: 999

Text #11

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5923. Min Act: -0.1689

Data Index: 4480416 (Open Web Text)

Max Activating Token Index: 1007

Text #12

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5787. Min Act: -0.1700

Data Index: 6264640 (Open Web Text)

Max Activating Token Index: 969

Text #13

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5885. Min Act: -0.1700

Data Index: 6971458 (Open Web Text)

Max Activating Token Index: 968

Text #14

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5571. Min Act: -0.1700

Data Index: 6261640 (Open Web Text)

Max Activating Token Index: 878

Text #15

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5193. Min Act: -0.1700

Data Index: 6261630 (Open Web Text)

Max Activating Token Index: 899

Text #16

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5082. Min Act: -0.1700

Data Index: 1427629 (Open Web Text)

Max Activating Token Index: 923

Text #17

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5552. Min Act: -0.1700

Data Index: 7944494 (Open Web Text)

Max Activating Token Index: 833

Text #18

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5213. Min Act: -0.1700

Data Index: 7458981 (Open Web Text)

Max Activating Token Index: 165

Text #19

Max Range: 3.7825. Min Range: -3.7825

Max Act: 3.5590. Min Act: -0.1700

Data Index: 3994746 (Open Web Text)

Max Activating Token Index: 222