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

Dataset: Open Web Text

Neuron 1436 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: 3.2652. Min Range: -3.2652

Max Act: 3.2443. Min Act: -0.1700

Data Index: 569342 (Open Web Text)

Max Activating Token Index: 42

Text #1

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.2652. Min Act: -0.1700

Data Index: 8332630 (Open Web Text)

Max Activating Token Index: 92

Text #2

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.2268. Min Act: -0.1700

Data Index: 3837812 (Open Web Text)

Max Activating Token Index: 438

Text #3

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1951. Min Act: -0.1700

Data Index: 668590 (Open Web Text)

Max Activating Token Index: 236

Text #4

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1878. Min Act: -0.1700

Data Index: 3408474 (Open Web Text)

Max Activating Token Index: 154

Text #5

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1766. Min Act: -0.1700

Data Index: 2596655 (Open Web Text)

Max Activating Token Index: 467

Text #6

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1506. Min Act: -0.1700

Data Index: 1732367 (Open Web Text)

Max Activating Token Index: 798

Text #7

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1846. Min Act: -0.1700

Data Index: 7097879 (Open Web Text)

Max Activating Token Index: 330

Text #8

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1903. Min Act: -0.1700

Data Index: 6493477 (Open Web Text)

Max Activating Token Index: 864

Text #9

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1856. Min Act: -0.1700

Data Index: 2939011 (Open Web Text)

Max Activating Token Index: 150

Text #10

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1660. Min Act: -0.1700

Data Index: 5816323 (Open Web Text)

Max Activating Token Index: 477

Text #11

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1574. Min Act: -0.1700

Data Index: 2446693 (Open Web Text)

Max Activating Token Index: 580

Text #12

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1661. Min Act: -0.1700

Data Index: 6700283 (Open Web Text)

Max Activating Token Index: 149

Text #13

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1771. Min Act: -0.1700

Data Index: 303287 (Open Web Text)

Max Activating Token Index: 497

Text #14

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1856. Min Act: -0.1700

Data Index: 3780171 (Open Web Text)

Max Activating Token Index: 840

Text #15

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1721. Min Act: -0.1700

Data Index: 8815313 (Open Web Text)

Max Activating Token Index: 594

Text #16

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1682. Min Act: -0.1700

Data Index: 1810743 (Open Web Text)

Max Activating Token Index: 262

Text #17

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1436. Min Act: -0.1700

Data Index: 7042016 (Open Web Text)

Max Activating Token Index: 84

Text #18

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1394. Min Act: -0.1700

Data Index: 4918775 (Open Web Text)

Max Activating Token Index: 212

Text #19

Max Range: 3.2652. Min Range: -3.2652

Max Act: 3.1536. Min Act: -0.1700

Data Index: 7952911 (Open Web Text)

Max Activating Token Index: 808