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

Dataset: Open Web Text

Neuron 923 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: 4.7951. Min Range: -4.7951

Max Act: 4.7951. Min Act: -0.1700

Data Index: 1875377 (Open Web Text)

Max Activating Token Index: 92

Text #1

Max Range: 4.7951. Min Range: -4.7951

Max Act: 4.7002. Min Act: -0.1700

Data Index: 8347316 (Open Web Text)

Max Activating Token Index: 191

Text #2

Max Range: 4.7951. Min Range: -4.7951

Max Act: 4.7887. Min Act: -0.1700

Data Index: 8735670 (Open Web Text)

Max Activating Token Index: 100

Text #3

Max Range: 4.7951. Min Range: -4.7951

Max Act: 4.7396. Min Act: -0.1700

Data Index: 2350176 (Open Web Text)

Max Activating Token Index: 332

Text #4

Max Range: 4.7951. Min Range: -4.7951

Max Act: 4.7165. Min Act: -0.1700

Data Index: 6682746 (Open Web Text)

Max Activating Token Index: 105

Text #5

Max Range: 4.7951. Min Range: -4.7951

Max Act: 4.6284. Min Act: -0.1700

Data Index: 8638503 (Open Web Text)

Max Activating Token Index: 477

Text #6

Max Range: 4.7951. Min Range: -4.7951

Max Act: 4.5528. Min Act: -0.1700

Data Index: 8076758 (Open Web Text)

Max Activating Token Index: 58

Text #7

Max Range: 4.7951. Min Range: -4.7951

Max Act: 4.6494. Min Act: -0.1700

Data Index: 7893033 (Open Web Text)

Max Activating Token Index: 536

Text #8

Max Range: 4.7951. Min Range: -4.7951

Max Act: 4.4708. Min Act: -0.1700

Data Index: 4470949 (Open Web Text)

Max Activating Token Index: 509

Text #9

Max Range: 4.7951. Min Range: -4.7951

Max Act: 4.6172. Min Act: -0.1700

Data Index: 499831 (Open Web Text)

Max Activating Token Index: 923

Text #10

Max Range: 4.7951. Min Range: -4.7951

Max Act: 4.5296. Min Act: -0.1700

Data Index: 6824028 (Open Web Text)

Max Activating Token Index: 428

Text #11

Max Range: 4.7951. Min Range: -4.7951

Max Act: 4.6581. Min Act: -0.1700

Data Index: 6889905 (Open Web Text)

Max Activating Token Index: 382

Text #12

Max Range: 4.7951. Min Range: -4.7951

Max Act: 4.5869. Min Act: -0.1700

Data Index: 5537068 (Open Web Text)

Max Activating Token Index: 224

Text #13

Max Range: 4.7951. Min Range: -4.7951

Max Act: 4.6210. Min Act: -0.1700

Data Index: 5387868 (Open Web Text)

Max Activating Token Index: 284

Text #14

Max Range: 4.7951. Min Range: -4.7951

Max Act: 4.4578. Min Act: -0.1700

Data Index: 8066394 (Open Web Text)

Max Activating Token Index: 584

Text #15

Max Range: 4.7951. Min Range: -4.7951

Max Act: 4.6047. Min Act: -0.1700

Data Index: 782889 (Open Web Text)

Max Activating Token Index: 410

Text #16

Max Range: 4.7951. Min Range: -4.7951

Max Act: 4.5184. Min Act: -0.1700

Data Index: 6058824 (Open Web Text)

Max Activating Token Index: 428

Text #17

Max Range: 4.7951. Min Range: -4.7951

Max Act: 4.5181. Min Act: -0.1700

Data Index: 5768722 (Open Web Text)

Max Activating Token Index: 788

Text #18

Max Range: 4.7951. Min Range: -4.7951

Max Act: 4.6349. Min Act: -0.1700

Data Index: 992384 (Open Web Text)

Max Activating Token Index: 551

Text #19

Max Range: 4.7951. Min Range: -4.7951

Max Act: 4.5508. Min Act: -0.1700

Data Index: 2032201 (Open Web Text)

Max Activating Token Index: 236