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

Dataset: Open Web Text

Neuron 437 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: 4.3149. Min Range: -4.3149

Max Act: 4.3149. Min Act: 0.1768

Data Index: 3001580 (Open Web Text)

Max Activating Token Index: 716

Text #1

Max Range: 4.3149. Min Range: -4.3149

Max Act: 4.2846. Min Act: 0.1311

Data Index: 3001581 (Open Web Text)

Max Activating Token Index: 498

Text #2

Max Range: 4.3149. Min Range: -4.3149

Max Act: 4.2488. Min Act: 0.0768

Data Index: 3001587 (Open Web Text)

Max Activating Token Index: 619

Text #3

Max Range: 4.3149. Min Range: -4.3149

Max Act: 4.2066. Min Act: 0.1747

Data Index: 3001578 (Open Web Text)

Max Activating Token Index: 835

Text #4

Max Range: 4.3149. Min Range: -4.3149

Max Act: 4.1825. Min Act: 0.1364

Data Index: 3001586 (Open Web Text)

Max Activating Token Index: 911

Text #5

Max Range: 4.3149. Min Range: -4.3149

Max Act: 4.0580. Min Act: 0.0861

Data Index: 3001583 (Open Web Text)

Max Activating Token Index: 826

Text #6

Max Range: 4.3149. Min Range: -4.3149

Max Act: 4.0410. Min Act: -0.0045

Data Index: 3001574 (Open Web Text)

Max Activating Token Index: 1002

Text #7

Max Range: 4.3149. Min Range: -4.3149

Max Act: 4.0153. Min Act: 0.5008

Data Index: 247241 (Open Web Text)

Max Activating Token Index: 846

Text #8

Max Range: 4.3149. Min Range: -4.3149

Max Act: 3.9773. Min Act: -0.1012

Data Index: 717174 (Open Web Text)

Max Activating Token Index: 260

Text #9

Max Range: 4.3149. Min Range: -4.3149

Max Act: 3.9578. Min Act: -0.1164

Data Index: 8526652 (Open Web Text)

Max Activating Token Index: 942

Text #10

Max Range: 4.3149. Min Range: -4.3149

Max Act: 3.9869. Min Act: 0.3384

Data Index: 8549500 (Open Web Text)

Max Activating Token Index: 186

Text #11

Max Range: 4.3149. Min Range: -4.3149

Max Act: 3.9455. Min Act: -0.1266

Data Index: 1989527 (Open Web Text)

Max Activating Token Index: 642

Text #12

Max Range: 4.3149. Min Range: -4.3149

Max Act: 3.9284. Min Act: -0.0946

Data Index: 4764357 (Open Web Text)

Max Activating Token Index: 713

Text #13

Max Range: 4.3149. Min Range: -4.3149

Max Act: 3.9240. Min Act: -0.1067

Data Index: 5172381 (Open Web Text)

Max Activating Token Index: 652

Text #14

Max Range: 4.3149. Min Range: -4.3149

Max Act: 3.9239. Min Act: 0.2700

Data Index: 4562647 (Open Web Text)

Max Activating Token Index: 377

Text #15

Max Range: 4.3149. Min Range: -4.3149

Max Act: 3.9074. Min Act: 0.0550

Data Index: 5564864 (Open Web Text)

Max Activating Token Index: 64

Text #16

Max Range: 4.3149. Min Range: -4.3149

Max Act: 3.9160. Min Act: -0.0520

Data Index: 8006457 (Open Web Text)

Max Activating Token Index: 524

Text #17

Max Range: 4.3149. Min Range: -4.3149

Max Act: 3.8944. Min Act: -0.1315

Data Index: 8120440 (Open Web Text)

Max Activating Token Index: 632

Text #18

Max Range: 4.3149. Min Range: -4.3149

Max Act: 3.8945. Min Act: 0.6753

Data Index: 1980666 (Open Web Text)

Max Activating Token Index: 810

Text #19

Max Range: 4.3149. Min Range: -4.3149

Max Act: 3.8961. Min Act: 0.0477

Data Index: 4501332 (Open Web Text)

Max Activating Token Index: 769