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

Dataset: Open Web Text

Neuron 649 in Layer 4

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: 3.2547. Min Range: -3.2547

Max Act: 3.2547. Min Act: -0.1700

Data Index: 8286113 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.2547. Min Act: -0.1700

Data Index: 5763718 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.2547. Min Act: -0.1700

Data Index: 7164704 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.2526. Min Act: -0.1700

Data Index: 3556102 (Open Web Text)

Max Activating Token Index: 387

Text #4

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.2204. Min Act: -0.1700

Data Index: 4184662 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.2204. Min Act: -0.1700

Data Index: 4184651 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.2204. Min Act: -0.1700

Data Index: 3649628 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.1830. Min Act: -0.1700

Data Index: 3981353 (Open Web Text)

Max Activating Token Index: 173

Text #8

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.1818. Min Act: -0.1700

Data Index: 2570060 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.1818. Min Act: -0.1700

Data Index: 1476921 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.1685. Min Act: -0.1700

Data Index: 969720 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.1564. Min Act: -0.1700

Data Index: 3754341 (Open Web Text)

Max Activating Token Index: 459

Text #12

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.1362. Min Act: -0.1700

Data Index: 8169551 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.1415. Min Act: -0.1700

Data Index: 8171563 (Open Web Text)

Max Activating Token Index: 310

Text #14

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.1166. Min Act: -0.1700

Data Index: 7177038 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.1191. Min Act: -0.1700

Data Index: 5315092 (Open Web Text)

Max Activating Token Index: 272

Text #16

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.1166. Min Act: -0.1700

Data Index: 1346550 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.1166. Min Act: -0.1700

Data Index: 5379511 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.1333. Min Act: -0.1700

Data Index: 4227778 (Open Web Text)

Max Activating Token Index: 893

Text #19

Max Range: 3.2547. Min Range: -3.2547

Max Act: 3.1166. Min Act: -0.1700

Data Index: 1090881 (Open Web Text)

Max Activating Token Index: 3