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

Dataset: Open Web Text

Neuron 60 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: 4.8443. Min Range: -4.8443

Max Act: 4.8443. Min Act: -0.1700

Data Index: 2182302 (Open Web Text)

Max Activating Token Index: 359

Text #1

Max Range: 4.8443. Min Range: -4.8443

Max Act: 4.7872. Min Act: -0.1700

Data Index: 5700182 (Open Web Text)

Max Activating Token Index: 928

Text #2

Max Range: 4.8443. Min Range: -4.8443

Max Act: 4.7690. Min Act: -0.1700

Data Index: 689012 (Open Web Text)

Max Activating Token Index: 744

Text #3

Max Range: 4.8443. Min Range: -4.8443

Max Act: 4.6867. Min Act: -0.1700

Data Index: 8801891 (Open Web Text)

Max Activating Token Index: 750

Text #4

Max Range: 4.8443. Min Range: -4.8443

Max Act: 4.7133. Min Act: -0.1700

Data Index: 8571861 (Open Web Text)

Max Activating Token Index: 705

Text #5

Max Range: 4.8443. Min Range: -4.8443

Max Act: 4.6679. Min Act: -0.1700

Data Index: 5004345 (Open Web Text)

Max Activating Token Index: 959

Text #6

Max Range: 4.8443. Min Range: -4.8443

Max Act: 4.6461. Min Act: -0.1700

Data Index: 2142997 (Open Web Text)

Max Activating Token Index: 993

Text #7

Max Range: 4.8443. Min Range: -4.8443

Max Act: 4.6444. Min Act: -0.1700

Data Index: 5362808 (Open Web Text)

Max Activating Token Index: 625

Text #8

Max Range: 4.8443. Min Range: -4.8443

Max Act: 4.6176. Min Act: -0.1700

Data Index: 2098257 (Open Web Text)

Max Activating Token Index: 553

Text #9

Max Range: 4.8443. Min Range: -4.8443

Max Act: 4.6336. Min Act: -0.1700

Data Index: 4479560 (Open Web Text)

Max Activating Token Index: 486

Text #10

Max Range: 4.8443. Min Range: -4.8443

Max Act: 4.5824. Min Act: -0.1700

Data Index: 4372957 (Open Web Text)

Max Activating Token Index: 677

Text #11

Max Range: 4.8443. Min Range: -4.8443

Max Act: 4.5711. Min Act: -0.1700

Data Index: 5741538 (Open Web Text)

Max Activating Token Index: 144

Text #12

Max Range: 4.8443. Min Range: -4.8443

Max Act: 4.5943. Min Act: -0.1700

Data Index: 2003639 (Open Web Text)

Max Activating Token Index: 434

Text #13

Max Range: 4.8443. Min Range: -4.8443

Max Act: 4.5870. Min Act: -0.1700

Data Index: 8641851 (Open Web Text)

Max Activating Token Index: 212

Text #14

Max Range: 4.8443. Min Range: -4.8443

Max Act: 4.6041. Min Act: -0.1700

Data Index: 4307920 (Open Web Text)

Max Activating Token Index: 518

Text #15

Max Range: 4.8443. Min Range: -4.8443

Max Act: 4.5990. Min Act: -0.1700

Data Index: 1736860 (Open Web Text)

Max Activating Token Index: 294

Text #16

Max Range: 4.8443. Min Range: -4.8443

Max Act: 4.5872. Min Act: -0.1700

Data Index: 41547 (Open Web Text)

Max Activating Token Index: 877

Text #17

Max Range: 4.8443. Min Range: -4.8443

Max Act: 4.6376. Min Act: -0.1700

Data Index: 4030508 (Open Web Text)

Max Activating Token Index: 778

Text #18

Max Range: 4.8443. Min Range: -4.8443

Max Act: 4.5750. Min Act: -0.1700

Data Index: 3003991 (Open Web Text)

Max Activating Token Index: 683

Text #19

Max Range: 4.8443. Min Range: -4.8443

Max Act: 4.6054. Min Act: -0.1700

Data Index: 3611264 (Open Web Text)

Max Activating Token Index: 744