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

Dataset: Open Web Text

Neuron 793 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: 4.7780. Min Range: -4.7780

Max Act: 4.7687. Min Act: -0.1700

Data Index: 8407816 (Open Web Text)

Max Activating Token Index: 789

Text #1

Max Range: 4.7780. Min Range: -4.7780

Max Act: 4.7780. Min Act: -0.1700

Data Index: 1981286 (Open Web Text)

Max Activating Token Index: 337

Text #2

Max Range: 4.7780. Min Range: -4.7780

Max Act: 4.7028. Min Act: -0.1700

Data Index: 1472666 (Open Web Text)

Max Activating Token Index: 79

Text #3

Max Range: 4.7780. Min Range: -4.7780

Max Act: 4.6835. Min Act: -0.1700

Data Index: 6941977 (Open Web Text)

Max Activating Token Index: 559

Text #4

Max Range: 4.7780. Min Range: -4.7780

Max Act: 4.7240. Min Act: -0.1700

Data Index: 7406713 (Open Web Text)

Max Activating Token Index: 471

Text #5

Max Range: 4.7780. Min Range: -4.7780

Max Act: 4.6777. Min Act: -0.1700

Data Index: 7556459 (Open Web Text)

Max Activating Token Index: 639

Text #6

Max Range: 4.7780. Min Range: -4.7780

Max Act: 4.6724. Min Act: -0.1700

Data Index: 5767504 (Open Web Text)

Max Activating Token Index: 209

Text #7

Max Range: 4.7780. Min Range: -4.7780

Max Act: 4.6456. Min Act: -0.1700

Data Index: 2953152 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 4.7780. Min Range: -4.7780

Max Act: 4.6554. Min Act: -0.1700

Data Index: 4908785 (Open Web Text)

Max Activating Token Index: 874

Text #9

Max Range: 4.7780. Min Range: -4.7780

Max Act: 4.6234. Min Act: -0.1700

Data Index: 2902125 (Open Web Text)

Max Activating Token Index: 330

Text #10

Max Range: 4.7780. Min Range: -4.7780

Max Act: 4.6199. Min Act: -0.1700

Data Index: 2967584 (Open Web Text)

Max Activating Token Index: 613

Text #11

Max Range: 4.7780. Min Range: -4.7780

Max Act: 4.6199. Min Act: -0.1700

Data Index: 3200739 (Open Web Text)

Max Activating Token Index: 540

Text #12

Max Range: 4.7780. Min Range: -4.7780

Max Act: 4.4880. Min Act: -0.1700

Data Index: 5466970 (Open Web Text)

Max Activating Token Index: 764

Text #13

Max Range: 4.7780. Min Range: -4.7780

Max Act: 4.5911. Min Act: -0.1700

Data Index: 7718040 (Open Web Text)

Max Activating Token Index: 847

Text #14

Max Range: 4.7780. Min Range: -4.7780

Max Act: 4.5576. Min Act: -0.1700

Data Index: 7750608 (Open Web Text)

Max Activating Token Index: 115

Text #15

Max Range: 4.7780. Min Range: -4.7780

Max Act: 4.5645. Min Act: -0.1700

Data Index: 2456303 (Open Web Text)

Max Activating Token Index: 658

Text #16

Max Range: 4.7780. Min Range: -4.7780

Max Act: 4.5387. Min Act: -0.1700

Data Index: 5226952 (Open Web Text)

Max Activating Token Index: 345

Text #17

Max Range: 4.7780. Min Range: -4.7780

Max Act: 4.5566. Min Act: -0.1700

Data Index: 2223247 (Open Web Text)

Max Activating Token Index: 727

Text #18

Max Range: 4.7780. Min Range: -4.7780

Max Act: 4.5506. Min Act: -0.1700

Data Index: 1365355 (Open Web Text)

Max Activating Token Index: 167

Text #19

Max Range: 4.7780. Min Range: -4.7780

Max Act: 4.5277. Min Act: -0.1700

Data Index: 12600 (Open Web Text)

Max Activating Token Index: 341