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

Dataset: Open Web Text

Neuron 1487 in Layer 2

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: 4.3328. Min Range: -4.3328

Max Act: 4.3328. Min Act: -0.1700

Data Index: 1774033 (Open Web Text)

Max Activating Token Index: 554

Text #1

Max Range: 4.3328. Min Range: -4.3328

Max Act: 4.1768. Min Act: -0.1700

Data Index: 5487504 (Open Web Text)

Max Activating Token Index: 181

Text #2

Max Range: 4.3328. Min Range: -4.3328

Max Act: 4.1614. Min Act: -0.1700

Data Index: 2743193 (Open Web Text)

Max Activating Token Index: 336

Text #3

Max Range: 4.3328. Min Range: -4.3328

Max Act: 4.1559. Min Act: -0.1700

Data Index: 4908561 (Open Web Text)

Max Activating Token Index: 45

Text #4

Max Range: 4.3328. Min Range: -4.3328

Max Act: 4.1128. Min Act: -0.1700

Data Index: 785582 (Open Web Text)

Max Activating Token Index: 119

Text #5

Max Range: 4.3328. Min Range: -4.3328

Max Act: 4.1125. Min Act: -0.1700

Data Index: 320233 (Open Web Text)

Max Activating Token Index: 155

Text #6

Max Range: 4.3328. Min Range: -4.3328

Max Act: 4.1030. Min Act: -0.1700

Data Index: 6079994 (Open Web Text)

Max Activating Token Index: 1016

Text #7

Max Range: 4.3328. Min Range: -4.3328

Max Act: 4.1062. Min Act: -0.1700

Data Index: 5392120 (Open Web Text)

Max Activating Token Index: 35

Text #8

Max Range: 4.3328. Min Range: -4.3328

Max Act: 4.1030. Min Act: -0.1700

Data Index: 6479416 (Open Web Text)

Max Activating Token Index: 348

Text #9

Max Range: 4.3328. Min Range: -4.3328

Max Act: 4.1359. Min Act: -0.1700

Data Index: 7461062 (Open Web Text)

Max Activating Token Index: 453

Text #10

Max Range: 4.3328. Min Range: -4.3328

Max Act: 4.0944. Min Act: -0.1700

Data Index: 8130838 (Open Web Text)

Max Activating Token Index: 521

Text #11

Max Range: 4.3328. Min Range: -4.3328

Max Act: 4.1193. Min Act: -0.1700

Data Index: 8233625 (Open Web Text)

Max Activating Token Index: 896

Text #12

Max Range: 4.3328. Min Range: -4.3328

Max Act: 4.0724. Min Act: -0.1700

Data Index: 1844677 (Open Web Text)

Max Activating Token Index: 336

Text #13

Max Range: 4.3328. Min Range: -4.3328

Max Act: 4.0745. Min Act: -0.1700

Data Index: 5344846 (Open Web Text)

Max Activating Token Index: 512

Text #14

Max Range: 4.3328. Min Range: -4.3328

Max Act: 4.0834. Min Act: -0.1700

Data Index: 1043504 (Open Web Text)

Max Activating Token Index: 580

Text #15

Max Range: 4.3328. Min Range: -4.3328

Max Act: 4.1110. Min Act: -0.1700

Data Index: 3681648 (Open Web Text)

Max Activating Token Index: 97

Text #16

Max Range: 4.3328. Min Range: -4.3328

Max Act: 4.0841. Min Act: -0.1700

Data Index: 2622662 (Open Web Text)

Max Activating Token Index: 104

Text #17

Max Range: 4.3328. Min Range: -4.3328

Max Act: 4.0916. Min Act: -0.1700

Data Index: 5791271 (Open Web Text)

Max Activating Token Index: 1018

Text #18

Max Range: 4.3328. Min Range: -4.3328

Max Act: 4.0946. Min Act: -0.1700

Data Index: 1865290 (Open Web Text)

Max Activating Token Index: 1015

Text #19

Max Range: 4.3328. Min Range: -4.3328

Max Act: 4.0614. Min Act: -0.1700

Data Index: 1833509 (Open Web Text)

Max Activating Token Index: 17