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

Dataset: Open Web Text

Neuron 794 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: 4.5337. Min Range: -4.5337

Max Act: 4.5337. Min Act: -0.1700

Data Index: 3973582 (Open Web Text)

Max Activating Token Index: 105

Text #1

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.4814. Min Act: -0.1700

Data Index: 7642043 (Open Web Text)

Max Activating Token Index: 128

Text #2

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.4727. Min Act: -0.1700

Data Index: 5828948 (Open Web Text)

Max Activating Token Index: 146

Text #3

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.5074. Min Act: -0.1700

Data Index: 8119553 (Open Web Text)

Max Activating Token Index: 451

Text #4

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.4672. Min Act: -0.1700

Data Index: 375786 (Open Web Text)

Max Activating Token Index: 774

Text #5

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.4296. Min Act: -0.1700

Data Index: 1705576 (Open Web Text)

Max Activating Token Index: 291

Text #6

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.4501. Min Act: -0.1700

Data Index: 6636921 (Open Web Text)

Max Activating Token Index: 424

Text #7

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.4365. Min Act: -0.1700

Data Index: 7410965 (Open Web Text)

Max Activating Token Index: 883

Text #8

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.4017. Min Act: -0.1700

Data Index: 3492949 (Open Web Text)

Max Activating Token Index: 868

Text #9

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.3867. Min Act: -0.1700

Data Index: 1738044 (Open Web Text)

Max Activating Token Index: 389

Text #10

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.3461. Min Act: -0.1700

Data Index: 6245638 (Open Web Text)

Max Activating Token Index: 105

Text #11

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.3564. Min Act: -0.1700

Data Index: 1540367 (Open Web Text)

Max Activating Token Index: 517

Text #12

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.3050. Min Act: -0.1700

Data Index: 8646446 (Open Web Text)

Max Activating Token Index: 402

Text #13

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.2876. Min Act: -0.1700

Data Index: 1677377 (Open Web Text)

Max Activating Token Index: 212

Text #14

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.2075. Min Act: -0.1700

Data Index: 6110041 (Open Web Text)

Max Activating Token Index: 854

Text #15

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.3017. Min Act: -0.1700

Data Index: 519288 (Open Web Text)

Max Activating Token Index: 386

Text #16

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.2134. Min Act: -0.1700

Data Index: 1980227 (Open Web Text)

Max Activating Token Index: 653

Text #17

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.2488. Min Act: -0.1700

Data Index: 4544170 (Open Web Text)

Max Activating Token Index: 195

Text #18

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.2688. Min Act: -0.1700

Data Index: 2734296 (Open Web Text)

Max Activating Token Index: 277

Text #19

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.2546. Min Act: -0.1700

Data Index: 4509619 (Open Web Text)

Max Activating Token Index: 438