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

Dataset: Open Web Text

Neuron 32 in Layer 0

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: 4.4860. Min Range: -4.4860

Max Act: 4.4860. Min Act: -0.1700

Data Index: 4531839 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.4618. Min Act: -0.1700

Data Index: 6098621 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.4288. Min Act: -0.1700

Data Index: 8562835 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.4245. Min Act: -0.1700

Data Index: 4749524 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.3846. Min Act: -0.1700

Data Index: 6377977 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.3751. Min Act: -0.1700

Data Index: 5189662 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.3444. Min Act: -0.1700

Data Index: 6408132 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.3315. Min Act: -0.1700

Data Index: 7056985 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.3234. Min Act: -0.1700

Data Index: 2726129 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.3359. Min Act: -0.1700

Data Index: 5396383 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.3056. Min Act: -0.1700

Data Index: 3487380 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.3186. Min Act: -0.1700

Data Index: 5848844 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.3242. Min Act: -0.1700

Data Index: 8390146 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.3085. Min Act: -0.1700

Data Index: 8452369 (Open Web Text)

Max Activating Token Index: 437

Text #14

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.3023. Min Act: -0.1700

Data Index: 4189615 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.2638. Min Act: -0.1700

Data Index: 6340235 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.2813. Min Act: -0.1700

Data Index: 4605635 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.2706. Min Act: -0.1700

Data Index: 6595411 (Open Web Text)

Max Activating Token Index: 628

Text #18

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.2843. Min Act: -0.1700

Data Index: 7534105 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.4860. Min Range: -4.4860

Max Act: 4.2860. Min Act: -0.1700

Data Index: 1668095 (Open Web Text)

Max Activating Token Index: 8