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

Dataset: Open Web Text

Neuron 495 in Layer 2

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: 4.3065. Min Range: -4.3065

Max Act: 4.3065. Min Act: -0.1700

Data Index: 8512564 (Open Web Text)

Max Activating Token Index: 127

Text #1

Max Range: 4.3065. Min Range: -4.3065

Max Act: 3.9589. Min Act: -0.1700

Data Index: 3678224 (Open Web Text)

Max Activating Token Index: 848

Text #2

Max Range: 4.3065. Min Range: -4.3065

Max Act: 3.9105. Min Act: -0.1700

Data Index: 7826739 (Open Web Text)

Max Activating Token Index: 527

Text #3

Max Range: 4.3065. Min Range: -4.3065

Max Act: 3.9131. Min Act: -0.1700

Data Index: 927869 (Open Web Text)

Max Activating Token Index: 95

Text #4

Max Range: 4.3065. Min Range: -4.3065

Max Act: 3.8657. Min Act: -0.1700

Data Index: 5732189 (Open Web Text)

Max Activating Token Index: 738

Text #5

Max Range: 4.3065. Min Range: -4.3065

Max Act: 3.8283. Min Act: -0.1700

Data Index: 7250855 (Open Web Text)

Max Activating Token Index: 139

Text #6

Max Range: 4.3065. Min Range: -4.3065

Max Act: 3.8394. Min Act: -0.1700

Data Index: 468351 (Open Web Text)

Max Activating Token Index: 544

Text #7

Max Range: 4.3065. Min Range: -4.3065

Max Act: 3.8410. Min Act: -0.1700

Data Index: 6701959 (Open Web Text)

Max Activating Token Index: 88

Text #8

Max Range: 4.3065. Min Range: -4.3065

Max Act: 3.8300. Min Act: -0.1700

Data Index: 6299245 (Open Web Text)

Max Activating Token Index: 48

Text #9

Max Range: 4.3065. Min Range: -4.3065

Max Act: 3.8163. Min Act: -0.1700

Data Index: 6713568 (Open Web Text)

Max Activating Token Index: 725

Text #10

Max Range: 4.3065. Min Range: -4.3065

Max Act: 3.7902. Min Act: -0.1700

Data Index: 6001557 (Open Web Text)

Max Activating Token Index: 174

Text #11

Max Range: 4.3065. Min Range: -4.3065

Max Act: 3.7636. Min Act: -0.1700

Data Index: 2410123 (Open Web Text)

Max Activating Token Index: 132

Text #12

Max Range: 4.3065. Min Range: -4.3065

Max Act: 3.7335. Min Act: -0.1700

Data Index: 5010866 (Open Web Text)

Max Activating Token Index: 73

Text #13

Max Range: 4.3065. Min Range: -4.3065

Max Act: 3.7435. Min Act: -0.1700

Data Index: 3490030 (Open Web Text)

Max Activating Token Index: 100

Text #14

Max Range: 4.3065. Min Range: -4.3065

Max Act: 3.7397. Min Act: -0.1700

Data Index: 873286 (Open Web Text)

Max Activating Token Index: 808

Text #15

Max Range: 4.3065. Min Range: -4.3065

Max Act: 3.7413. Min Act: -0.1700

Data Index: 8436834 (Open Web Text)

Max Activating Token Index: 123

Text #16

Max Range: 4.3065. Min Range: -4.3065

Max Act: 3.7515. Min Act: -0.1700

Data Index: 3032607 (Open Web Text)

Max Activating Token Index: 299

Text #17

Max Range: 4.3065. Min Range: -4.3065

Max Act: 3.7349. Min Act: -0.1700

Data Index: 4542579 (Open Web Text)

Max Activating Token Index: 859

Text #18

Max Range: 4.3065. Min Range: -4.3065

Max Act: 3.7095. Min Act: -0.1700

Data Index: 4302434 (Open Web Text)

Max Activating Token Index: 35

Text #19

Max Range: 4.3065. Min Range: -4.3065

Max Act: 3.7167. Min Act: -0.1700

Data Index: 5826844 (Open Web Text)

Max Activating Token Index: 618