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

Dataset: Open Web Text

Neuron 2468 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: 3.0148. Min Range: -3.0148

Max Act: 3.0148. Min Act: -0.1700

Data Index: 5967225 (Open Web Text)

Max Activating Token Index: 337

Text #1

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.9446. Min Act: -0.1700

Data Index: 6575078 (Open Web Text)

Max Activating Token Index: 566

Text #2

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8720. Min Act: -0.1700

Data Index: 8267091 (Open Web Text)

Max Activating Token Index: 1013

Text #3

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.9143. Min Act: -0.1700

Data Index: 3239034 (Open Web Text)

Max Activating Token Index: 704

Text #4

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8767. Min Act: -0.1700

Data Index: 8345728 (Open Web Text)

Max Activating Token Index: 916

Text #5

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.9112. Min Act: -0.1700

Data Index: 5408050 (Open Web Text)

Max Activating Token Index: 887

Text #6

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8710. Min Act: -0.1700

Data Index: 774681 (Open Web Text)

Max Activating Token Index: 309

Text #7

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8866. Min Act: -0.1700

Data Index: 5604874 (Open Web Text)

Max Activating Token Index: 219

Text #8

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8799. Min Act: -0.1700

Data Index: 5944524 (Open Web Text)

Max Activating Token Index: 123

Text #9

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8372. Min Act: -0.1700

Data Index: 7902536 (Open Web Text)

Max Activating Token Index: 526

Text #10

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8700. Min Act: -0.1700

Data Index: 6098128 (Open Web Text)

Max Activating Token Index: 994

Text #11

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8722. Min Act: -0.1700

Data Index: 1577244 (Open Web Text)

Max Activating Token Index: 46

Text #12

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8663. Min Act: -0.1700

Data Index: 6666721 (Open Web Text)

Max Activating Token Index: 776

Text #13

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8407. Min Act: -0.1700

Data Index: 7513195 (Open Web Text)

Max Activating Token Index: 318

Text #14

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8185. Min Act: -0.1700

Data Index: 6388970 (Open Web Text)

Max Activating Token Index: 875

Text #15

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8329. Min Act: -0.1700

Data Index: 3973192 (Open Web Text)

Max Activating Token Index: 77

Text #16

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8200. Min Act: -0.1700

Data Index: 2491998 (Open Web Text)

Max Activating Token Index: 658

Text #17

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.7995. Min Act: -0.1700

Data Index: 2715809 (Open Web Text)

Max Activating Token Index: 657

Text #18

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.8390. Min Act: -0.1700

Data Index: 553531 (Open Web Text)

Max Activating Token Index: 822

Text #19

Max Range: 3.0148. Min Range: -3.0148

Max Act: 2.7814. Min Act: -0.1700

Data Index: 4827619 (Open Web Text)

Max Activating Token Index: 763