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

Dataset: Open Web Text

Neuron 2139 in Layer 6

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: 12.0124. Min Range: -12.0124

Max Act: 12.0124. Min Act: -0.1700

Data Index: 6602869 (Open Web Text)

Max Activating Token Index: 428

Text #1

Max Range: 12.0124. Min Range: -12.0124

Max Act: 11.7168. Min Act: -0.1700

Data Index: 6019842 (Open Web Text)

Max Activating Token Index: 575

Text #2

Max Range: 12.0124. Min Range: -12.0124

Max Act: 11.5687. Min Act: -0.1700

Data Index: 4147588 (Open Web Text)

Max Activating Token Index: 427

Text #3

Max Range: 12.0124. Min Range: -12.0124

Max Act: 11.2592. Min Act: -0.1700

Data Index: 8342025 (Open Web Text)

Max Activating Token Index: 245

Text #4

Max Range: 12.0124. Min Range: -12.0124

Max Act: 11.3582. Min Act: -0.1700

Data Index: 2670317 (Open Web Text)

Max Activating Token Index: 490

Text #5

Max Range: 12.0124. Min Range: -12.0124

Max Act: 10.8988. Min Act: -0.1700

Data Index: 4251182 (Open Web Text)

Max Activating Token Index: 500

Text #6

Max Range: 12.0124. Min Range: -12.0124

Max Act: 10.9511. Min Act: -0.1700

Data Index: 5769218 (Open Web Text)

Max Activating Token Index: 353

Text #7

Max Range: 12.0124. Min Range: -12.0124

Max Act: 10.9896. Min Act: -0.1698

Data Index: 477665 (Open Web Text)

Max Activating Token Index: 756

Text #8

Max Range: 12.0124. Min Range: -12.0124

Max Act: 10.9308. Min Act: -0.1700

Data Index: 1767087 (Open Web Text)

Max Activating Token Index: 722

Text #9

Max Range: 12.0124. Min Range: -12.0124

Max Act: 10.8793. Min Act: -0.1700

Data Index: 4164808 (Open Web Text)

Max Activating Token Index: 300

Text #10

Max Range: 12.0124. Min Range: -12.0124

Max Act: 10.7161. Min Act: -0.1700

Data Index: 1828949 (Open Web Text)

Max Activating Token Index: 486

Text #11

Max Range: 12.0124. Min Range: -12.0124

Max Act: 10.7605. Min Act: -0.1700

Data Index: 3764583 (Open Web Text)

Max Activating Token Index: 366

Text #12

Max Range: 12.0124. Min Range: -12.0124

Max Act: 10.6782. Min Act: -0.1700

Data Index: 297209 (Open Web Text)

Max Activating Token Index: 501

Text #13

Max Range: 12.0124. Min Range: -12.0124

Max Act: 10.7195. Min Act: -0.1686

Data Index: 1155593 (Open Web Text)

Max Activating Token Index: 536

Text #14

Max Range: 12.0124. Min Range: -12.0124

Max Act: 10.7053. Min Act: -0.1700

Data Index: 3386324 (Open Web Text)

Max Activating Token Index: 268

Text #15

Max Range: 12.0124. Min Range: -12.0124

Max Act: 10.6182. Min Act: -0.1699

Data Index: 831766 (Open Web Text)

Max Activating Token Index: 956

Text #16

Max Range: 12.0124. Min Range: -12.0124

Max Act: 10.6218. Min Act: -0.1697

Data Index: 618514 (Open Web Text)

Max Activating Token Index: 509

Text #17

Max Range: 12.0124. Min Range: -12.0124

Max Act: 10.4355. Min Act: -0.1700

Data Index: 4610247 (Open Web Text)

Max Activating Token Index: 934

Text #18

Max Range: 12.0124. Min Range: -12.0124

Max Act: 10.5035. Min Act: -0.1700

Data Index: 710165 (Open Web Text)

Max Activating Token Index: 437

Text #19

Max Range: 12.0124. Min Range: -12.0124

Max Act: 10.5965. Min Act: -0.1700

Data Index: 5210077 (Open Web Text)

Max Activating Token Index: 142