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

Dataset: Open Web Text

Neuron 1636 in Layer 6

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: 5.2047. Min Range: -5.2047

Max Act: 5.2047. Min Act: -0.1700

Data Index: 5419623 (Open Web Text)

Max Activating Token Index: 887

Text #1

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.0884. Min Act: -0.1700

Data Index: 6172763 (Open Web Text)

Max Activating Token Index: 47

Text #2

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.0175. Min Act: -0.1700

Data Index: 8430278 (Open Web Text)

Max Activating Token Index: 340

Text #3

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.0257. Min Act: -0.1700

Data Index: 4438758 (Open Web Text)

Max Activating Token Index: 787

Text #4

Max Range: 5.2047. Min Range: -5.2047

Max Act: 5.0196. Min Act: -0.1700

Data Index: 2712156 (Open Web Text)

Max Activating Token Index: 278

Text #5

Max Range: 5.2047. Min Range: -5.2047

Max Act: 4.9381. Min Act: -0.1700

Data Index: 2751563 (Open Web Text)

Max Activating Token Index: 263

Text #6

Max Range: 5.2047. Min Range: -5.2047

Max Act: 4.9102. Min Act: -0.1700

Data Index: 4201259 (Open Web Text)

Max Activating Token Index: 268

Text #7

Max Range: 5.2047. Min Range: -5.2047

Max Act: 4.9427. Min Act: -0.1700

Data Index: 6624734 (Open Web Text)

Max Activating Token Index: 707

Text #8

Max Range: 5.2047. Min Range: -5.2047

Max Act: 4.8066. Min Act: -0.1700

Data Index: 7368214 (Open Web Text)

Max Activating Token Index: 878

Text #9

Max Range: 5.2047. Min Range: -5.2047

Max Act: 4.8764. Min Act: -0.1700

Data Index: 6331171 (Open Web Text)

Max Activating Token Index: 107

Text #10

Max Range: 5.2047. Min Range: -5.2047

Max Act: 4.8296. Min Act: -0.1700

Data Index: 6372396 (Open Web Text)

Max Activating Token Index: 142

Text #11

Max Range: 5.2047. Min Range: -5.2047

Max Act: 4.7665. Min Act: -0.1700

Data Index: 3247934 (Open Web Text)

Max Activating Token Index: 213

Text #12

Max Range: 5.2047. Min Range: -5.2047

Max Act: 4.7803. Min Act: -0.1700

Data Index: 5766201 (Open Web Text)

Max Activating Token Index: 379

Text #13

Max Range: 5.2047. Min Range: -5.2047

Max Act: 4.8227. Min Act: -0.1700

Data Index: 104437 (Open Web Text)

Max Activating Token Index: 487

Text #14

Max Range: 5.2047. Min Range: -5.2047

Max Act: 4.7964. Min Act: -0.1700

Data Index: 2118541 (Open Web Text)

Max Activating Token Index: 393

Text #15

Max Range: 5.2047. Min Range: -5.2047

Max Act: 4.8058. Min Act: -0.1700

Data Index: 7390897 (Open Web Text)

Max Activating Token Index: 501

Text #16

Max Range: 5.2047. Min Range: -5.2047

Max Act: 4.7575. Min Act: -0.1700

Data Index: 8148957 (Open Web Text)

Max Activating Token Index: 916

Text #17

Max Range: 5.2047. Min Range: -5.2047

Max Act: 4.7876. Min Act: -0.1700

Data Index: 5312656 (Open Web Text)

Max Activating Token Index: 446

Text #18

Max Range: 5.2047. Min Range: -5.2047

Max Act: 4.7978. Min Act: -0.1700

Data Index: 8147418 (Open Web Text)

Max Activating Token Index: 712

Text #19

Max Range: 5.2047. Min Range: -5.2047

Max Act: 4.7718. Min Act: -0.1700

Data Index: 5833287 (Open Web Text)

Max Activating Token Index: 639