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

Dataset: Open Web Text

Neuron 1994 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: 5.2420. Min Range: -5.2420

Max Act: 5.2420. Min Act: -0.1700

Data Index: 2769946 (Open Web Text)

Max Activating Token Index: 295

Text #1

Max Range: 5.2420. Min Range: -5.2420

Max Act: 5.1634. Min Act: -0.1700

Data Index: 5906220 (Open Web Text)

Max Activating Token Index: 257

Text #2

Max Range: 5.2420. Min Range: -5.2420

Max Act: 4.9610. Min Act: -0.1700

Data Index: 3745881 (Open Web Text)

Max Activating Token Index: 258

Text #3

Max Range: 5.2420. Min Range: -5.2420

Max Act: 4.9349. Min Act: -0.1700

Data Index: 5501164 (Open Web Text)

Max Activating Token Index: 399

Text #4

Max Range: 5.2420. Min Range: -5.2420

Max Act: 4.8724. Min Act: -0.1700

Data Index: 131346 (Open Web Text)

Max Activating Token Index: 760

Text #5

Max Range: 5.2420. Min Range: -5.2420

Max Act: 4.8981. Min Act: -0.1700

Data Index: 5128770 (Open Web Text)

Max Activating Token Index: 207

Text #6

Max Range: 5.2420. Min Range: -5.2420

Max Act: 4.8879. Min Act: -0.1700

Data Index: 6182114 (Open Web Text)

Max Activating Token Index: 131

Text #7

Max Range: 5.2420. Min Range: -5.2420

Max Act: 4.8900. Min Act: -0.1700

Data Index: 1275169 (Open Web Text)

Max Activating Token Index: 501

Text #8

Max Range: 5.2420. Min Range: -5.2420

Max Act: 4.8616. Min Act: -0.1700

Data Index: 5395088 (Open Web Text)

Max Activating Token Index: 307

Text #9

Max Range: 5.2420. Min Range: -5.2420

Max Act: 4.8824. Min Act: -0.1700

Data Index: 8136051 (Open Web Text)

Max Activating Token Index: 1004

Text #10

Max Range: 5.2420. Min Range: -5.2420

Max Act: 4.8218. Min Act: -0.1700

Data Index: 2724272 (Open Web Text)

Max Activating Token Index: 871

Text #11

Max Range: 5.2420. Min Range: -5.2420

Max Act: 4.7729. Min Act: -0.1700

Data Index: 3736626 (Open Web Text)

Max Activating Token Index: 92

Text #12

Max Range: 5.2420. Min Range: -5.2420

Max Act: 4.8093. Min Act: -0.1700

Data Index: 8197979 (Open Web Text)

Max Activating Token Index: 691

Text #13

Max Range: 5.2420. Min Range: -5.2420

Max Act: 4.7539. Min Act: -0.1700

Data Index: 7930043 (Open Web Text)

Max Activating Token Index: 494

Text #14

Max Range: 5.2420. Min Range: -5.2420

Max Act: 4.8145. Min Act: -0.1700

Data Index: 4465219 (Open Web Text)

Max Activating Token Index: 705

Text #15

Max Range: 5.2420. Min Range: -5.2420

Max Act: 4.8091. Min Act: -0.1700

Data Index: 1072104 (Open Web Text)

Max Activating Token Index: 352

Text #16

Max Range: 5.2420. Min Range: -5.2420

Max Act: 4.8370. Min Act: -0.1700

Data Index: 1400630 (Open Web Text)

Max Activating Token Index: 207

Text #17

Max Range: 5.2420. Min Range: -5.2420

Max Act: 4.8304. Min Act: -0.1700

Data Index: 3373985 (Open Web Text)

Max Activating Token Index: 438

Text #18

Max Range: 5.2420. Min Range: -5.2420

Max Act: 4.8686. Min Act: -0.1700

Data Index: 3745880 (Open Web Text)

Max Activating Token Index: 739

Text #19

Max Range: 5.2420. Min Range: -5.2420

Max Act: 4.7794. Min Act: -0.1700

Data Index: 2953156 (Open Web Text)

Max Activating Token Index: 81