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

Dataset: Open Web Text

Neuron 1925 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: 4.1891. Min Range: -4.1891

Max Act: 4.1891. Min Act: -0.1700

Data Index: 7381909 (Open Web Text)

Max Activating Token Index: 620

Text #1

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0978. Min Act: -0.1700

Data Index: 2139835 (Open Web Text)

Max Activating Token Index: 215

Text #2

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.1052. Min Act: -0.1700

Data Index: 2150688 (Open Web Text)

Max Activating Token Index: 665

Text #3

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0872. Min Act: -0.1700

Data Index: 4469176 (Open Web Text)

Max Activating Token Index: 294

Text #4

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0709. Min Act: -0.1700

Data Index: 4815253 (Open Web Text)

Max Activating Token Index: 614

Text #5

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0630. Min Act: -0.1700

Data Index: 1413062 (Open Web Text)

Max Activating Token Index: 91

Text #6

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0770. Min Act: -0.1700

Data Index: 958212 (Open Web Text)

Max Activating Token Index: 229

Text #7

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0300. Min Act: -0.1700

Data Index: 1335300 (Open Web Text)

Max Activating Token Index: 660

Text #8

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0133. Min Act: -0.1700

Data Index: 6988049 (Open Web Text)

Max Activating Token Index: 248

Text #9

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0077. Min Act: -0.1700

Data Index: 1692226 (Open Web Text)

Max Activating Token Index: 621

Text #10

Max Range: 4.1891. Min Range: -4.1891

Max Act: 3.9999. Min Act: -0.1700

Data Index: 2399039 (Open Web Text)

Max Activating Token Index: 732

Text #11

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0282. Min Act: -0.1700

Data Index: 114198 (Open Web Text)

Max Activating Token Index: 128

Text #12

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0186. Min Act: -0.1700

Data Index: 941603 (Open Web Text)

Max Activating Token Index: 738

Text #13

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0048. Min Act: -0.1700

Data Index: 935075 (Open Web Text)

Max Activating Token Index: 321

Text #14

Max Range: 4.1891. Min Range: -4.1891

Max Act: 3.9903. Min Act: -0.1700

Data Index: 1655562 (Open Web Text)

Max Activating Token Index: 19

Text #15

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0113. Min Act: -0.1700

Data Index: 8411181 (Open Web Text)

Max Activating Token Index: 467

Text #16

Max Range: 4.1891. Min Range: -4.1891

Max Act: 3.9948. Min Act: -0.1700

Data Index: 3623065 (Open Web Text)

Max Activating Token Index: 780

Text #17

Max Range: 4.1891. Min Range: -4.1891

Max Act: 3.9783. Min Act: -0.1700

Data Index: 506600 (Open Web Text)

Max Activating Token Index: 173

Text #18

Max Range: 4.1891. Min Range: -4.1891

Max Act: 3.9805. Min Act: -0.1700

Data Index: 4038748 (Open Web Text)

Max Activating Token Index: 784

Text #19

Max Range: 4.1891. Min Range: -4.1891

Max Act: 4.0029. Min Act: -0.1700

Data Index: 4197526 (Open Web Text)

Max Activating Token Index: 562