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

Dataset: Open Web Text

Neuron 2732 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: 3.0213. Min Range: -3.0213

Max Act: 3.0213. Min Act: -0.1700

Data Index: 6238720 (Open Web Text)

Max Activating Token Index: 989

Text #1

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.9989. Min Act: -0.1700

Data Index: 6349586 (Open Web Text)

Max Activating Token Index: 895

Text #2

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.9637. Min Act: -0.1700

Data Index: 3025193 (Open Web Text)

Max Activating Token Index: 869

Text #3

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.9607. Min Act: -0.1700

Data Index: 4941400 (Open Web Text)

Max Activating Token Index: 745

Text #4

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.9554. Min Act: -0.1700

Data Index: 5619119 (Open Web Text)

Max Activating Token Index: 474

Text #5

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.9591. Min Act: -0.1700

Data Index: 2198904 (Open Web Text)

Max Activating Token Index: 695

Text #6

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.9342. Min Act: -0.1700

Data Index: 6277681 (Open Web Text)

Max Activating Token Index: 410

Text #7

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.9446. Min Act: -0.1700

Data Index: 7143404 (Open Web Text)

Max Activating Token Index: 419

Text #8

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.9404. Min Act: -0.1700

Data Index: 6280185 (Open Web Text)

Max Activating Token Index: 563

Text #9

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.9143. Min Act: -0.1700

Data Index: 1767726 (Open Web Text)

Max Activating Token Index: 83

Text #10

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.9142. Min Act: -0.1700

Data Index: 6511653 (Open Web Text)

Max Activating Token Index: 783

Text #11

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.8935. Min Act: -0.1700

Data Index: 4718044 (Open Web Text)

Max Activating Token Index: 190

Text #12

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.8978. Min Act: -0.1700

Data Index: 6965554 (Open Web Text)

Max Activating Token Index: 159

Text #13

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.9109. Min Act: -0.1700

Data Index: 3451616 (Open Web Text)

Max Activating Token Index: 424

Text #14

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.8985. Min Act: -0.1700

Data Index: 151825 (Open Web Text)

Max Activating Token Index: 587

Text #15

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.8744. Min Act: -0.1700

Data Index: 4938693 (Open Web Text)

Max Activating Token Index: 525

Text #16

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.8775. Min Act: -0.1700

Data Index: 7977784 (Open Web Text)

Max Activating Token Index: 947

Text #17

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.8788. Min Act: -0.1700

Data Index: 150498 (Open Web Text)

Max Activating Token Index: 687

Text #18

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.8694. Min Act: -0.1700

Data Index: 3730056 (Open Web Text)

Max Activating Token Index: 660

Text #19

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.8660. Min Act: -0.1700

Data Index: 220642 (Open Web Text)

Max Activating Token Index: 672