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

Dataset: Open Web Text

Neuron 1852 in Layer 1

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: 1.8054. Min Range: -1.8054

Max Act: 1.8054. Min Act: -0.1700

Data Index: 1527297 (Open Web Text)

Max Activating Token Index: 67

Text #1

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7881. Min Act: -0.1700

Data Index: 2557053 (Open Web Text)

Max Activating Token Index: 325

Text #2

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7717. Min Act: -0.1700

Data Index: 887458 (Open Web Text)

Max Activating Token Index: 598

Text #3

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7597. Min Act: -0.1700

Data Index: 5043964 (Open Web Text)

Max Activating Token Index: 722

Text #4

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7636. Min Act: -0.1700

Data Index: 2473616 (Open Web Text)

Max Activating Token Index: 38

Text #5

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7644. Min Act: -0.1700

Data Index: 6288607 (Open Web Text)

Max Activating Token Index: 76

Text #6

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7419. Min Act: -0.1700

Data Index: 6153467 (Open Web Text)

Max Activating Token Index: 624

Text #7

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7408. Min Act: -0.1700

Data Index: 1807601 (Open Web Text)

Max Activating Token Index: 250

Text #8

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7471. Min Act: -0.1700

Data Index: 3558228 (Open Web Text)

Max Activating Token Index: 23

Text #9

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7451. Min Act: -0.1699

Data Index: 8120913 (Open Web Text)

Max Activating Token Index: 672

Text #10

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7447. Min Act: -0.1700

Data Index: 6410200 (Open Web Text)

Max Activating Token Index: 681

Text #11

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7397. Min Act: -0.1700

Data Index: 3260393 (Open Web Text)

Max Activating Token Index: 623

Text #12

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7346. Min Act: -0.1700

Data Index: 1703925 (Open Web Text)

Max Activating Token Index: 68

Text #13

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7375. Min Act: -0.1700

Data Index: 5882568 (Open Web Text)

Max Activating Token Index: 228

Text #14

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7340. Min Act: -0.1700

Data Index: 4130795 (Open Web Text)

Max Activating Token Index: 561

Text #15

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7213. Min Act: -0.1700

Data Index: 5344610 (Open Web Text)

Max Activating Token Index: 353

Text #16

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7195. Min Act: -0.1700

Data Index: 5766940 (Open Web Text)

Max Activating Token Index: 490

Text #17

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7138. Min Act: -0.1700

Data Index: 5109842 (Open Web Text)

Max Activating Token Index: 995

Text #18

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7097. Min Act: -0.1700

Data Index: 3497138 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 1.8054. Min Range: -1.8054

Max Act: 1.7165. Min Act: -0.1700

Data Index: 4328531 (Open Web Text)

Max Activating Token Index: 687