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

Dataset: Open Web Text

Neuron 1841 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: 3.5754. Min Range: -3.5754

Max Act: 3.5754. Min Act: -0.1700

Data Index: 5883752 (Open Web Text)

Max Activating Token Index: 464

Text #1

Max Range: 3.5754. Min Range: -3.5754

Max Act: 3.5174. Min Act: -0.1700

Data Index: 4572067 (Open Web Text)

Max Activating Token Index: 331

Text #2

Max Range: 3.5754. Min Range: -3.5754

Max Act: 3.5310. Min Act: -0.1700

Data Index: 8280530 (Open Web Text)

Max Activating Token Index: 745

Text #3

Max Range: 3.5754. Min Range: -3.5754

Max Act: 3.4774. Min Act: -0.1700

Data Index: 7421521 (Open Web Text)

Max Activating Token Index: 516

Text #4

Max Range: 3.5754. Min Range: -3.5754

Max Act: 3.4726. Min Act: -0.1700

Data Index: 2345791 (Open Web Text)

Max Activating Token Index: 45

Text #5

Max Range: 3.5754. Min Range: -3.5754

Max Act: 3.4387. Min Act: -0.1700

Data Index: 607728 (Open Web Text)

Max Activating Token Index: 603

Text #6

Max Range: 3.5754. Min Range: -3.5754

Max Act: 3.3997. Min Act: -0.1700

Data Index: 7828404 (Open Web Text)

Max Activating Token Index: 801

Text #7

Max Range: 3.5754. Min Range: -3.5754

Max Act: 3.4094. Min Act: -0.1700

Data Index: 2292805 (Open Web Text)

Max Activating Token Index: 501

Text #8

Max Range: 3.5754. Min Range: -3.5754

Max Act: 3.3981. Min Act: -0.1700

Data Index: 1110276 (Open Web Text)

Max Activating Token Index: 668

Text #9

Max Range: 3.5754. Min Range: -3.5754

Max Act: 3.4129. Min Act: -0.1700

Data Index: 3770737 (Open Web Text)

Max Activating Token Index: 598

Text #10

Max Range: 3.5754. Min Range: -3.5754

Max Act: 3.3835. Min Act: -0.1700

Data Index: 4755099 (Open Web Text)

Max Activating Token Index: 875

Text #11

Max Range: 3.5754. Min Range: -3.5754

Max Act: 3.3987. Min Act: -0.1700

Data Index: 7668507 (Open Web Text)

Max Activating Token Index: 879

Text #12

Max Range: 3.5754. Min Range: -3.5754

Max Act: 3.3757. Min Act: -0.1700

Data Index: 3584769 (Open Web Text)

Max Activating Token Index: 689

Text #13

Max Range: 3.5754. Min Range: -3.5754

Max Act: 3.3610. Min Act: -0.1700

Data Index: 5007024 (Open Web Text)

Max Activating Token Index: 741

Text #14

Max Range: 3.5754. Min Range: -3.5754

Max Act: 3.3556. Min Act: -0.1700

Data Index: 2335036 (Open Web Text)

Max Activating Token Index: 733

Text #15

Max Range: 3.5754. Min Range: -3.5754

Max Act: 3.3341. Min Act: -0.1700

Data Index: 3847085 (Open Web Text)

Max Activating Token Index: 426

Text #16

Max Range: 3.5754. Min Range: -3.5754

Max Act: 3.3497. Min Act: -0.1700

Data Index: 1474781 (Open Web Text)

Max Activating Token Index: 653

Text #17

Max Range: 3.5754. Min Range: -3.5754

Max Act: 3.2994. Min Act: -0.1700

Data Index: 6051149 (Open Web Text)

Max Activating Token Index: 495

Text #18

Max Range: 3.5754. Min Range: -3.5754

Max Act: 3.3221. Min Act: -0.1700

Data Index: 2024561 (Open Web Text)

Max Activating Token Index: 643

Text #19

Max Range: 3.5754. Min Range: -3.5754

Max Act: 3.3052. Min Act: -0.1700

Data Index: 6656195 (Open Web Text)

Max Activating Token Index: 421