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

Dataset: Open Web Text

Neuron 2631 in Layer 1

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: 1.8338. Min Range: -1.8338

Max Act: 1.8275. Min Act: -0.1700

Data Index: 4839254 (Open Web Text)

Max Activating Token Index: 504

Text #1

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.8081. Min Act: -0.1700

Data Index: 5055151 (Open Web Text)

Max Activating Token Index: 514

Text #2

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.8338. Min Act: -0.1700

Data Index: 1410538 (Open Web Text)

Max Activating Token Index: 644

Text #3

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.7957. Min Act: -0.1700

Data Index: 3750509 (Open Web Text)

Max Activating Token Index: 767

Text #4

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.8036. Min Act: -0.1700

Data Index: 1925660 (Open Web Text)

Max Activating Token Index: 596

Text #5

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.7811. Min Act: -0.1700

Data Index: 6515613 (Open Web Text)

Max Activating Token Index: 150

Text #6

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.7758. Min Act: -0.1700

Data Index: 2479400 (Open Web Text)

Max Activating Token Index: 258

Text #7

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.7532. Min Act: -0.1700

Data Index: 1069 (Open Web Text)

Max Activating Token Index: 756

Text #8

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.7579. Min Act: -0.1700

Data Index: 5324498 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.7547. Min Act: -0.1700

Data Index: 2678707 (Open Web Text)

Max Activating Token Index: 793

Text #10

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.7492. Min Act: -0.1700

Data Index: 2991024 (Open Web Text)

Max Activating Token Index: 959

Text #11

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.7200. Min Act: -0.1700

Data Index: 1032672 (Open Web Text)

Max Activating Token Index: 859

Text #12

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.7339. Min Act: -0.1700

Data Index: 5822009 (Open Web Text)

Max Activating Token Index: 461

Text #13

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.7183. Min Act: -0.1700

Data Index: 6418046 (Open Web Text)

Max Activating Token Index: 70

Text #14

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.7358. Min Act: -0.1700

Data Index: 677078 (Open Web Text)

Max Activating Token Index: 130

Text #15

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.7122. Min Act: -0.1700

Data Index: 4987536 (Open Web Text)

Max Activating Token Index: 938

Text #16

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.7203. Min Act: -0.1700

Data Index: 4923029 (Open Web Text)

Max Activating Token Index: 60

Text #17

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.7083. Min Act: -0.1700

Data Index: 984225 (Open Web Text)

Max Activating Token Index: 757

Text #18

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.7442. Min Act: -0.1700

Data Index: 2834116 (Open Web Text)

Max Activating Token Index: 488

Text #19

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.7137. Min Act: -0.1700

Data Index: 2769182 (Open Web Text)

Max Activating Token Index: 4