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

Dataset: Open Web Text

Neuron 2770 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: 4.5593. Min Range: -4.5593

Max Act: 4.5593. Min Act: -0.1700

Data Index: 5425657 (Open Web Text)

Max Activating Token Index: 507

Text #1

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.5500. Min Act: -0.1700

Data Index: 3431793 (Open Web Text)

Max Activating Token Index: 802

Text #2

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.5303. Min Act: -0.1700

Data Index: 1582018 (Open Web Text)

Max Activating Token Index: 785

Text #3

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.4920. Min Act: -0.1700

Data Index: 2248870 (Open Web Text)

Max Activating Token Index: 86

Text #4

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.4871. Min Act: -0.1700

Data Index: 1785095 (Open Web Text)

Max Activating Token Index: 496

Text #5

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.4661. Min Act: -0.1700

Data Index: 6057628 (Open Web Text)

Max Activating Token Index: 451

Text #6

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.4441. Min Act: -0.1700

Data Index: 3758912 (Open Web Text)

Max Activating Token Index: 502

Text #7

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.3961. Min Act: -0.1700

Data Index: 7938446 (Open Web Text)

Max Activating Token Index: 188

Text #8

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.4005. Min Act: -0.1700

Data Index: 8257601 (Open Web Text)

Max Activating Token Index: 328

Text #9

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.3746. Min Act: -0.1700

Data Index: 4262802 (Open Web Text)

Max Activating Token Index: 953

Text #10

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.3571. Min Act: -0.1700

Data Index: 2883371 (Open Web Text)

Max Activating Token Index: 742

Text #11

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.3609. Min Act: -0.1700

Data Index: 2846286 (Open Web Text)

Max Activating Token Index: 358

Text #12

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.3357. Min Act: -0.1700

Data Index: 8208477 (Open Web Text)

Max Activating Token Index: 953

Text #13

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.3221. Min Act: -0.1700

Data Index: 5877053 (Open Web Text)

Max Activating Token Index: 425

Text #14

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.3474. Min Act: -0.1700

Data Index: 8406318 (Open Web Text)

Max Activating Token Index: 833

Text #15

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.3166. Min Act: -0.1700

Data Index: 5806358 (Open Web Text)

Max Activating Token Index: 300

Text #16

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.3112. Min Act: -0.1700

Data Index: 2229929 (Open Web Text)

Max Activating Token Index: 425

Text #17

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.2897. Min Act: -0.1700

Data Index: 3937188 (Open Web Text)

Max Activating Token Index: 498

Text #18

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.3041. Min Act: -0.1700

Data Index: 1528678 (Open Web Text)

Max Activating Token Index: 902

Text #19

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.2938. Min Act: -0.1700

Data Index: 375441 (Open Web Text)

Max Activating Token Index: 703