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

Dataset: Open Web Text

Neuron 2598 in Layer 2

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: 3.7240. Min Range: -3.7240

Max Act: 3.7240. Min Act: -0.1700

Data Index: 6426961 (Open Web Text)

Max Activating Token Index: 241

Text #1

Max Range: 3.7240. Min Range: -3.7240

Max Act: 3.5891. Min Act: -0.1700

Data Index: 2947008 (Open Web Text)

Max Activating Token Index: 574

Text #2

Max Range: 3.7240. Min Range: -3.7240

Max Act: 3.6623. Min Act: -0.1700

Data Index: 1989328 (Open Web Text)

Max Activating Token Index: 203

Text #3

Max Range: 3.7240. Min Range: -3.7240

Max Act: 3.6048. Min Act: -0.1700

Data Index: 2819606 (Open Web Text)

Max Activating Token Index: 423

Text #4

Max Range: 3.7240. Min Range: -3.7240

Max Act: 3.6862. Min Act: -0.1700

Data Index: 2595179 (Open Web Text)

Max Activating Token Index: 588

Text #5

Max Range: 3.7240. Min Range: -3.7240

Max Act: 3.6150. Min Act: -0.1700

Data Index: 538912 (Open Web Text)

Max Activating Token Index: 436

Text #6

Max Range: 3.7240. Min Range: -3.7240

Max Act: 3.6096. Min Act: -0.1700

Data Index: 2955814 (Open Web Text)

Max Activating Token Index: 323

Text #7

Max Range: 3.7240. Min Range: -3.7240

Max Act: 3.5601. Min Act: -0.1700

Data Index: 6923191 (Open Web Text)

Max Activating Token Index: 595

Text #8

Max Range: 3.7240. Min Range: -3.7240

Max Act: 3.5548. Min Act: -0.1700

Data Index: 7046421 (Open Web Text)

Max Activating Token Index: 504

Text #9

Max Range: 3.7240. Min Range: -3.7240

Max Act: 3.5156. Min Act: -0.1700

Data Index: 4984942 (Open Web Text)

Max Activating Token Index: 454

Text #10

Max Range: 3.7240. Min Range: -3.7240

Max Act: 3.6139. Min Act: -0.1700

Data Index: 706272 (Open Web Text)

Max Activating Token Index: 739

Text #11

Max Range: 3.7240. Min Range: -3.7240

Max Act: 3.5984. Min Act: -0.1700

Data Index: 4697684 (Open Web Text)

Max Activating Token Index: 411

Text #12

Max Range: 3.7240. Min Range: -3.7240

Max Act: 3.5444. Min Act: -0.1700

Data Index: 5393917 (Open Web Text)

Max Activating Token Index: 670

Text #13

Max Range: 3.7240. Min Range: -3.7240

Max Act: 3.6008. Min Act: -0.1700

Data Index: 1203789 (Open Web Text)

Max Activating Token Index: 791

Text #14

Max Range: 3.7240. Min Range: -3.7240

Max Act: 3.5391. Min Act: -0.1700

Data Index: 2846073 (Open Web Text)

Max Activating Token Index: 74

Text #15

Max Range: 3.7240. Min Range: -3.7240

Max Act: 3.5726. Min Act: -0.1700

Data Index: 985930 (Open Web Text)

Max Activating Token Index: 598

Text #16

Max Range: 3.7240. Min Range: -3.7240

Max Act: 3.5821. Min Act: -0.1700

Data Index: 3931202 (Open Web Text)

Max Activating Token Index: 851

Text #17

Max Range: 3.7240. Min Range: -3.7240

Max Act: 3.5405. Min Act: -0.1700

Data Index: 6357087 (Open Web Text)

Max Activating Token Index: 114

Text #18

Max Range: 3.7240. Min Range: -3.7240

Max Act: 3.5500. Min Act: -0.1700

Data Index: 3051512 (Open Web Text)

Max Activating Token Index: 235

Text #19

Max Range: 3.7240. Min Range: -3.7240

Max Act: 3.6046. Min Act: -0.1700

Data Index: 3158847 (Open Web Text)

Max Activating Token Index: 236