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

Dataset: Open Web Text

Neuron 405 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: 2.2160. Min Range: -2.2160

Max Act: 2.2099. Min Act: -0.1700

Data Index: 6213880 (Open Web Text)

Max Activating Token Index: 672

Text #1

Max Range: 2.2160. Min Range: -2.2160

Max Act: 2.2160. Min Act: -0.1700

Data Index: 3181858 (Open Web Text)

Max Activating Token Index: 496

Text #2

Max Range: 2.2160. Min Range: -2.2160

Max Act: 2.1637. Min Act: -0.1700

Data Index: 1856233 (Open Web Text)

Max Activating Token Index: 521

Text #3

Max Range: 2.2160. Min Range: -2.2160

Max Act: 2.1671. Min Act: -0.1700

Data Index: 116327 (Open Web Text)

Max Activating Token Index: 455

Text #4

Max Range: 2.2160. Min Range: -2.2160

Max Act: 2.0993. Min Act: -0.1700

Data Index: 5096100 (Open Web Text)

Max Activating Token Index: 361

Text #5

Max Range: 2.2160. Min Range: -2.2160

Max Act: 2.0986. Min Act: -0.1698

Data Index: 4753731 (Open Web Text)

Max Activating Token Index: 434

Text #6

Max Range: 2.2160. Min Range: -2.2160

Max Act: 2.1001. Min Act: -0.1700

Data Index: 4537903 (Open Web Text)

Max Activating Token Index: 338

Text #7

Max Range: 2.2160. Min Range: -2.2160

Max Act: 2.1085. Min Act: -0.1700

Data Index: 949854 (Open Web Text)

Max Activating Token Index: 574

Text #8

Max Range: 2.2160. Min Range: -2.2160

Max Act: 2.1018. Min Act: -0.1700

Data Index: 755391 (Open Web Text)

Max Activating Token Index: 1015

Text #9

Max Range: 2.2160. Min Range: -2.2160

Max Act: 2.0840. Min Act: -0.1700

Data Index: 1503896 (Open Web Text)

Max Activating Token Index: 162

Text #10

Max Range: 2.2160. Min Range: -2.2160

Max Act: 2.0963. Min Act: -0.1700

Data Index: 3017358 (Open Web Text)

Max Activating Token Index: 707

Text #11

Max Range: 2.2160. Min Range: -2.2160

Max Act: 2.0908. Min Act: -0.1700

Data Index: 4674901 (Open Web Text)

Max Activating Token Index: 361

Text #12

Max Range: 2.2160. Min Range: -2.2160

Max Act: 2.0927. Min Act: -0.1700

Data Index: 1866741 (Open Web Text)

Max Activating Token Index: 22

Text #13

Max Range: 2.2160. Min Range: -2.2160

Max Act: 2.0963. Min Act: -0.1700

Data Index: 6392125 (Open Web Text)

Max Activating Token Index: 104

Text #14

Max Range: 2.2160. Min Range: -2.2160

Max Act: 2.0796. Min Act: -0.1700

Data Index: 957663 (Open Web Text)

Max Activating Token Index: 226

Text #15

Max Range: 2.2160. Min Range: -2.2160

Max Act: 2.0721. Min Act: -0.1700

Data Index: 2970786 (Open Web Text)

Max Activating Token Index: 213

Text #16

Max Range: 2.2160. Min Range: -2.2160

Max Act: 2.0710. Min Act: -0.1700

Data Index: 3009925 (Open Web Text)

Max Activating Token Index: 621

Text #17

Max Range: 2.2160. Min Range: -2.2160

Max Act: 2.0712. Min Act: -0.1700

Data Index: 2495115 (Open Web Text)

Max Activating Token Index: 761

Text #18

Max Range: 2.2160. Min Range: -2.2160

Max Act: 2.0679. Min Act: -0.1700

Data Index: 2226362 (Open Web Text)

Max Activating Token Index: 983

Text #19

Max Range: 2.2160. Min Range: -2.2160

Max Act: 2.0792. Min Act: -0.1700

Data Index: 4151390 (Open Web Text)

Max Activating Token Index: 62