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

Dataset: Open Web Text

Neuron 634 in Layer 3

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: 3.6848. Min Range: -3.6848

Max Act: 3.6673. Min Act: -0.1700

Data Index: 2455153 (Open Web Text)

Max Activating Token Index: 225

Text #1

Max Range: 3.6848. Min Range: -3.6848

Max Act: 3.6848. Min Act: -0.1700

Data Index: 3219013 (Open Web Text)

Max Activating Token Index: 926

Text #2

Max Range: 3.6848. Min Range: -3.6848

Max Act: 3.6330. Min Act: -0.1700

Data Index: 3879190 (Open Web Text)

Max Activating Token Index: 446

Text #3

Max Range: 3.6848. Min Range: -3.6848

Max Act: 3.6116. Min Act: -0.1700

Data Index: 2112035 (Open Web Text)

Max Activating Token Index: 383

Text #4

Max Range: 3.6848. Min Range: -3.6848

Max Act: 3.6411. Min Act: -0.1700

Data Index: 8536250 (Open Web Text)

Max Activating Token Index: 537

Text #5

Max Range: 3.6848. Min Range: -3.6848

Max Act: 3.6052. Min Act: -0.1700

Data Index: 7027761 (Open Web Text)

Max Activating Token Index: 201

Text #6

Max Range: 3.6848. Min Range: -3.6848

Max Act: 3.5732. Min Act: -0.1700

Data Index: 759486 (Open Web Text)

Max Activating Token Index: 616

Text #7

Max Range: 3.6848. Min Range: -3.6848

Max Act: 3.5816. Min Act: -0.1700

Data Index: 5902954 (Open Web Text)

Max Activating Token Index: 551

Text #8

Max Range: 3.6848. Min Range: -3.6848

Max Act: 3.5438. Min Act: -0.1700

Data Index: 1674862 (Open Web Text)

Max Activating Token Index: 55

Text #9

Max Range: 3.6848. Min Range: -3.6848

Max Act: 3.5716. Min Act: -0.1700

Data Index: 3882825 (Open Web Text)

Max Activating Token Index: 617

Text #10

Max Range: 3.6848. Min Range: -3.6848

Max Act: 3.5673. Min Act: -0.1700

Data Index: 5566568 (Open Web Text)

Max Activating Token Index: 646

Text #11

Max Range: 3.6848. Min Range: -3.6848

Max Act: 3.5071. Min Act: -0.1700

Data Index: 5056893 (Open Web Text)

Max Activating Token Index: 623

Text #12

Max Range: 3.6848. Min Range: -3.6848

Max Act: 3.5411. Min Act: -0.1700

Data Index: 4644180 (Open Web Text)

Max Activating Token Index: 214

Text #13

Max Range: 3.6848. Min Range: -3.6848

Max Act: 3.5470. Min Act: -0.1700

Data Index: 630631 (Open Web Text)

Max Activating Token Index: 469

Text #14

Max Range: 3.6848. Min Range: -3.6848

Max Act: 3.5254. Min Act: -0.1700

Data Index: 8208542 (Open Web Text)

Max Activating Token Index: 982

Text #15

Max Range: 3.6848. Min Range: -3.6848

Max Act: 3.4863. Min Act: -0.1700

Data Index: 1868093 (Open Web Text)

Max Activating Token Index: 174

Text #16

Max Range: 3.6848. Min Range: -3.6848

Max Act: 3.5196. Min Act: -0.1700

Data Index: 6036562 (Open Web Text)

Max Activating Token Index: 92

Text #17

Max Range: 3.6848. Min Range: -3.6848

Max Act: 3.4985. Min Act: -0.1700

Data Index: 4495793 (Open Web Text)

Max Activating Token Index: 175

Text #18

Max Range: 3.6848. Min Range: -3.6848

Max Act: 3.4506. Min Act: -0.1700

Data Index: 6281200 (Open Web Text)

Max Activating Token Index: 505

Text #19

Max Range: 3.6848. Min Range: -3.6848

Max Act: 3.4885. Min Act: -0.1700

Data Index: 3064525 (Open Web Text)

Max Activating Token Index: 922