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

Dataset: Open Web Text

Neuron 1633 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: 4.1368. Min Range: -4.1368

Max Act: 4.1368. Min Act: -0.1700

Data Index: 3935756 (Open Web Text)

Max Activating Token Index: 121

Text #1

Max Range: 4.1368. Min Range: -4.1368

Max Act: 4.1158. Min Act: -0.1700

Data Index: 7291832 (Open Web Text)

Max Activating Token Index: 429

Text #2

Max Range: 4.1368. Min Range: -4.1368

Max Act: 4.0616. Min Act: -0.1700

Data Index: 7648513 (Open Web Text)

Max Activating Token Index: 896

Text #3

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9842. Min Act: -0.1700

Data Index: 7317470 (Open Web Text)

Max Activating Token Index: 923

Text #4

Max Range: 4.1368. Min Range: -4.1368

Max Act: 4.0075. Min Act: -0.1700

Data Index: 2687297 (Open Web Text)

Max Activating Token Index: 447

Text #5

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9734. Min Act: -0.1700

Data Index: 8804278 (Open Web Text)

Max Activating Token Index: 323

Text #6

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9989. Min Act: -0.1700

Data Index: 3514645 (Open Web Text)

Max Activating Token Index: 415

Text #7

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9804. Min Act: -0.1700

Data Index: 3062228 (Open Web Text)

Max Activating Token Index: 21

Text #8

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9608. Min Act: -0.1700

Data Index: 5350944 (Open Web Text)

Max Activating Token Index: 760

Text #9

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9856. Min Act: -0.1700

Data Index: 580380 (Open Web Text)

Max Activating Token Index: 424

Text #10

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9862. Min Act: -0.1700

Data Index: 5045498 (Open Web Text)

Max Activating Token Index: 242

Text #11

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9325. Min Act: -0.1700

Data Index: 3034672 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9793. Min Act: -0.1700

Data Index: 4349309 (Open Web Text)

Max Activating Token Index: 517

Text #13

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9946. Min Act: -0.1700

Data Index: 4169146 (Open Web Text)

Max Activating Token Index: 199

Text #14

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9559. Min Act: -0.1700

Data Index: 8230873 (Open Web Text)

Max Activating Token Index: 327

Text #15

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9293. Min Act: -0.1700

Data Index: 3439673 (Open Web Text)

Max Activating Token Index: 215

Text #16

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9274. Min Act: -0.1700

Data Index: 6291422 (Open Web Text)

Max Activating Token Index: 978

Text #17

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9284. Min Act: -0.1700

Data Index: 142620 (Open Web Text)

Max Activating Token Index: 985

Text #18

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9156. Min Act: -0.1700

Data Index: 1900123 (Open Web Text)

Max Activating Token Index: 430

Text #19

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9371. Min Act: -0.1700

Data Index: 754018 (Open Web Text)

Max Activating Token Index: 876