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

Dataset: Open Web Text

Neuron 791 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: 4.4162. Min Range: -4.4162

Max Act: 4.4162. Min Act: -0.1700

Data Index: 1053384 (Open Web Text)

Max Activating Token Index: 111

Text #1

Max Range: 4.4162. Min Range: -4.4162

Max Act: 4.3470. Min Act: -0.1700

Data Index: 1677429 (Open Web Text)

Max Activating Token Index: 50

Text #2

Max Range: 4.4162. Min Range: -4.4162

Max Act: 4.3436. Min Act: -0.1700

Data Index: 1589330 (Open Web Text)

Max Activating Token Index: 45

Text #3

Max Range: 4.4162. Min Range: -4.4162

Max Act: 4.3055. Min Act: -0.1700

Data Index: 1134027 (Open Web Text)

Max Activating Token Index: 797

Text #4

Max Range: 4.4162. Min Range: -4.4162

Max Act: 4.3331. Min Act: -0.1700

Data Index: 8218356 (Open Web Text)

Max Activating Token Index: 210

Text #5

Max Range: 4.4162. Min Range: -4.4162

Max Act: 4.2716. Min Act: -0.1700

Data Index: 7788058 (Open Web Text)

Max Activating Token Index: 167

Text #6

Max Range: 4.4162. Min Range: -4.4162

Max Act: 4.2971. Min Act: -0.1700

Data Index: 718001 (Open Web Text)

Max Activating Token Index: 14

Text #7

Max Range: 4.4162. Min Range: -4.4162

Max Act: 4.2129. Min Act: -0.1700

Data Index: 2411680 (Open Web Text)

Max Activating Token Index: 847

Text #8

Max Range: 4.4162. Min Range: -4.4162

Max Act: 4.2665. Min Act: -0.1700

Data Index: 1521762 (Open Web Text)

Max Activating Token Index: 58

Text #9

Max Range: 4.4162. Min Range: -4.4162

Max Act: 4.2447. Min Act: -0.1700

Data Index: 4734536 (Open Web Text)

Max Activating Token Index: 79

Text #10

Max Range: 4.4162. Min Range: -4.4162

Max Act: 4.2885. Min Act: -0.1700

Data Index: 8171095 (Open Web Text)

Max Activating Token Index: 202

Text #11

Max Range: 4.4162. Min Range: -4.4162

Max Act: 4.2671. Min Act: -0.1700

Data Index: 4458579 (Open Web Text)

Max Activating Token Index: 17

Text #12

Max Range: 4.4162. Min Range: -4.4162

Max Act: 4.2829. Min Act: -0.1700

Data Index: 7193534 (Open Web Text)

Max Activating Token Index: 159

Text #13

Max Range: 4.4162. Min Range: -4.4162

Max Act: 4.2189. Min Act: -0.1700

Data Index: 6036785 (Open Web Text)

Max Activating Token Index: 825

Text #14

Max Range: 4.4162. Min Range: -4.4162

Max Act: 4.2201. Min Act: -0.1700

Data Index: 4462596 (Open Web Text)

Max Activating Token Index: 19

Text #15

Max Range: 4.4162. Min Range: -4.4162

Max Act: 4.2495. Min Act: -0.1700

Data Index: 4767009 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.4162. Min Range: -4.4162

Max Act: 4.2236. Min Act: -0.1700

Data Index: 5387066 (Open Web Text)

Max Activating Token Index: 839

Text #17

Max Range: 4.4162. Min Range: -4.4162

Max Act: 4.2157. Min Act: -0.1700

Data Index: 3916806 (Open Web Text)

Max Activating Token Index: 567

Text #18

Max Range: 4.4162. Min Range: -4.4162

Max Act: 4.2101. Min Act: -0.1700

Data Index: 6100408 (Open Web Text)

Max Activating Token Index: 855

Text #19

Max Range: 4.4162. Min Range: -4.4162

Max Act: 4.2463. Min Act: -0.1700

Data Index: 3765691 (Open Web Text)

Max Activating Token Index: 775