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

Dataset: Open Web Text

Neuron 1191 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: 2.3535. Min Range: -2.3535

Max Act: 2.3535. Min Act: -0.1700

Data Index: 2709944 (Open Web Text)

Max Activating Token Index: 379

Text #1

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.3042. Min Act: -0.1700

Data Index: 4492425 (Open Web Text)

Max Activating Token Index: 475

Text #2

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.3093. Min Act: -0.1700

Data Index: 7528921 (Open Web Text)

Max Activating Token Index: 319

Text #3

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.2701. Min Act: -0.1700

Data Index: 7670881 (Open Web Text)

Max Activating Token Index: 98

Text #4

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.2392. Min Act: -0.1700

Data Index: 2473854 (Open Web Text)

Max Activating Token Index: 534

Text #5

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.2208. Min Act: -0.1700

Data Index: 6340510 (Open Web Text)

Max Activating Token Index: 742

Text #6

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.2230. Min Act: -0.1700

Data Index: 2370018 (Open Web Text)

Max Activating Token Index: 831

Text #7

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.2275. Min Act: -0.1700

Data Index: 97927 (Open Web Text)

Max Activating Token Index: 757

Text #8

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.2042. Min Act: -0.1700

Data Index: 5572570 (Open Web Text)

Max Activating Token Index: 851

Text #9

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.1784. Min Act: -0.1700

Data Index: 3891395 (Open Web Text)

Max Activating Token Index: 410

Text #10

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.1799. Min Act: -0.1700

Data Index: 5666297 (Open Web Text)

Max Activating Token Index: 278

Text #11

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.1689. Min Act: -0.1700

Data Index: 2767689 (Open Web Text)

Max Activating Token Index: 432

Text #12

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.1390. Min Act: -0.1700

Data Index: 7667932 (Open Web Text)

Max Activating Token Index: 798

Text #13

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.1498. Min Act: -0.1700

Data Index: 3349270 (Open Web Text)

Max Activating Token Index: 978

Text #14

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.1461. Min Act: -0.1700

Data Index: 4401955 (Open Web Text)

Max Activating Token Index: 823

Text #15

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.1405. Min Act: -0.1700

Data Index: 475528 (Open Web Text)

Max Activating Token Index: 66

Text #16

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.1150. Min Act: -0.1700

Data Index: 8382005 (Open Web Text)

Max Activating Token Index: 707

Text #17

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.1296. Min Act: -0.1700

Data Index: 5427231 (Open Web Text)

Max Activating Token Index: 520

Text #18

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.1123. Min Act: -0.1700

Data Index: 5284800 (Open Web Text)

Max Activating Token Index: 758

Text #19

Max Range: 2.3535. Min Range: -2.3535

Max Act: 2.1136. Min Act: -0.1700

Data Index: 327797 (Open Web Text)

Max Activating Token Index: 853