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

Dataset: Open Web Text

Neuron 1076 in Layer 3

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: 3.7137. Min Range: -3.7137

Max Act: 3.7137. Min Act: -0.1700

Data Index: 6283437 (Open Web Text)

Max Activating Token Index: 860

Text #1

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.6488. Min Act: -0.1700

Data Index: 2770342 (Open Web Text)

Max Activating Token Index: 32

Text #2

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.6385. Min Act: -0.1700

Data Index: 1906252 (Open Web Text)

Max Activating Token Index: 22

Text #3

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.5861. Min Act: -0.1700

Data Index: 2429576 (Open Web Text)

Max Activating Token Index: 87

Text #4

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.6153. Min Act: -0.1700

Data Index: 8452804 (Open Web Text)

Max Activating Token Index: 661

Text #5

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.5984. Min Act: -0.1700

Data Index: 4459535 (Open Web Text)

Max Activating Token Index: 300

Text #6

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.5755. Min Act: -0.1700

Data Index: 8736647 (Open Web Text)

Max Activating Token Index: 712

Text #7

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.5437. Min Act: -0.1700

Data Index: 4446895 (Open Web Text)

Max Activating Token Index: 436

Text #8

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.6027. Min Act: -0.1700

Data Index: 2390806 (Open Web Text)

Max Activating Token Index: 349

Text #9

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.5120. Min Act: -0.1700

Data Index: 2899541 (Open Web Text)

Max Activating Token Index: 763

Text #10

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.5048. Min Act: -0.1700

Data Index: 6243509 (Open Web Text)

Max Activating Token Index: 15

Text #11

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.5199. Min Act: -0.1700

Data Index: 5893854 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.4868. Min Act: -0.1700

Data Index: 5761046 (Open Web Text)

Max Activating Token Index: 986

Text #13

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.5236. Min Act: -0.1700

Data Index: 4963277 (Open Web Text)

Max Activating Token Index: 375

Text #14

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.4866. Min Act: -0.1700

Data Index: 1224942 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.4886. Min Act: -0.1700

Data Index: 6017353 (Open Web Text)

Max Activating Token Index: 156

Text #16

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.4878. Min Act: -0.1700

Data Index: 4059376 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.4732. Min Act: -0.1700

Data Index: 924355 (Open Web Text)

Max Activating Token Index: 445

Text #18

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.5003. Min Act: -0.1700

Data Index: 3775574 (Open Web Text)

Max Activating Token Index: 324

Text #19

Max Range: 3.7137. Min Range: -3.7137

Max Act: 3.4676. Min Act: -0.1700

Data Index: 8214591 (Open Web Text)

Max Activating Token Index: 659