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

Dataset: Open Web Text

Neuron 150 in Layer 5

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: 2.6402. Min Range: -2.6402

Max Act: 2.6402. Min Act: -0.1700

Data Index: 1954974 (Open Web Text)

Max Activating Token Index: 443

Text #1

Max Range: 2.6402. Min Range: -2.6402

Max Act: 2.6258. Min Act: -0.1700

Data Index: 4498459 (Open Web Text)

Max Activating Token Index: 166

Text #2

Max Range: 2.6402. Min Range: -2.6402

Max Act: 2.5967. Min Act: -0.1700

Data Index: 133776 (Open Web Text)

Max Activating Token Index: 643

Text #3

Max Range: 2.6402. Min Range: -2.6402

Max Act: 2.5778. Min Act: -0.1700

Data Index: 5255068 (Open Web Text)

Max Activating Token Index: 404

Text #4

Max Range: 2.6402. Min Range: -2.6402

Max Act: 2.5877. Min Act: -0.1700

Data Index: 5029204 (Open Web Text)

Max Activating Token Index: 643

Text #5

Max Range: 2.6402. Min Range: -2.6402

Max Act: 2.5578. Min Act: -0.1700

Data Index: 2180058 (Open Web Text)

Max Activating Token Index: 570

Text #6

Max Range: 2.6402. Min Range: -2.6402

Max Act: 2.5423. Min Act: -0.1700

Data Index: 2215022 (Open Web Text)

Max Activating Token Index: 58

Text #7

Max Range: 2.6402. Min Range: -2.6402

Max Act: 2.5568. Min Act: -0.1700

Data Index: 3882599 (Open Web Text)

Max Activating Token Index: 106

Text #8

Max Range: 2.6402. Min Range: -2.6402

Max Act: 2.5259. Min Act: -0.1700

Data Index: 8827441 (Open Web Text)

Max Activating Token Index: 112

Text #9

Max Range: 2.6402. Min Range: -2.6402

Max Act: 2.5452. Min Act: -0.1700

Data Index: 3220617 (Open Web Text)

Max Activating Token Index: 374

Text #10

Max Range: 2.6402. Min Range: -2.6402

Max Act: 2.5147. Min Act: -0.1700

Data Index: 5518953 (Open Web Text)

Max Activating Token Index: 73

Text #11

Max Range: 2.6402. Min Range: -2.6402

Max Act: 2.5234. Min Act: -0.1700

Data Index: 4348805 (Open Web Text)

Max Activating Token Index: 710

Text #12

Max Range: 2.6402. Min Range: -2.6402

Max Act: 2.5139. Min Act: -0.1700

Data Index: 2872855 (Open Web Text)

Max Activating Token Index: 773

Text #13

Max Range: 2.6402. Min Range: -2.6402

Max Act: 2.5010. Min Act: -0.1700

Data Index: 6416988 (Open Web Text)

Max Activating Token Index: 916

Text #14

Max Range: 2.6402. Min Range: -2.6402

Max Act: 2.4929. Min Act: -0.1700

Data Index: 6172335 (Open Web Text)

Max Activating Token Index: 916

Text #15

Max Range: 2.6402. Min Range: -2.6402

Max Act: 2.4880. Min Act: -0.1700

Data Index: 4659342 (Open Web Text)

Max Activating Token Index: 272

Text #16

Max Range: 2.6402. Min Range: -2.6402

Max Act: 2.5135. Min Act: -0.1700

Data Index: 979759 (Open Web Text)

Max Activating Token Index: 781

Text #17

Max Range: 2.6402. Min Range: -2.6402

Max Act: 2.4741. Min Act: -0.1700

Data Index: 2266680 (Open Web Text)

Max Activating Token Index: 1016

Text #18

Max Range: 2.6402. Min Range: -2.6402

Max Act: 2.5169. Min Act: -0.1700

Data Index: 7324606 (Open Web Text)

Max Activating Token Index: 299

Text #19

Max Range: 2.6402. Min Range: -2.6402

Max Act: 2.4807. Min Act: -0.1700

Data Index: 2324510 (Open Web Text)

Max Activating Token Index: 142