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

Dataset: Open Web Text

Neuron 2749 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: 3.5024. Min Range: -3.5024

Max Act: 3.4938. Min Act: -0.1700

Data Index: 2586099 (Open Web Text)

Max Activating Token Index: 303

Text #1

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.4916. Min Act: -0.1700

Data Index: 2410108 (Open Web Text)

Max Activating Token Index: 88

Text #2

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.5024. Min Act: -0.1700

Data Index: 3146496 (Open Web Text)

Max Activating Token Index: 399

Text #3

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.4149. Min Act: -0.1700

Data Index: 6811524 (Open Web Text)

Max Activating Token Index: 1022

Text #4

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.4338. Min Act: -0.1700

Data Index: 744679 (Open Web Text)

Max Activating Token Index: 912

Text #5

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.3827. Min Act: -0.1700

Data Index: 350005 (Open Web Text)

Max Activating Token Index: 142

Text #6

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.3820. Min Act: -0.1700

Data Index: 3741471 (Open Web Text)

Max Activating Token Index: 808

Text #7

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.3898. Min Act: -0.1700

Data Index: 3486597 (Open Web Text)

Max Activating Token Index: 243

Text #8

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.3842. Min Act: -0.1700

Data Index: 467063 (Open Web Text)

Max Activating Token Index: 440

Text #9

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.3717. Min Act: -0.1700

Data Index: 4171079 (Open Web Text)

Max Activating Token Index: 472

Text #10

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.3689. Min Act: -0.1700

Data Index: 476241 (Open Web Text)

Max Activating Token Index: 602

Text #11

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.3503. Min Act: -0.1700

Data Index: 3654031 (Open Web Text)

Max Activating Token Index: 122

Text #12

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.3754. Min Act: -0.1700

Data Index: 8615011 (Open Web Text)

Max Activating Token Index: 860

Text #13

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.3687. Min Act: -0.1700

Data Index: 8274458 (Open Web Text)

Max Activating Token Index: 670

Text #14

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.3595. Min Act: -0.1700

Data Index: 4495931 (Open Web Text)

Max Activating Token Index: 179

Text #15

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.3723. Min Act: -0.1700

Data Index: 3769820 (Open Web Text)

Max Activating Token Index: 786

Text #16

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.3355. Min Act: -0.1700

Data Index: 4228095 (Open Web Text)

Max Activating Token Index: 430

Text #17

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.3404. Min Act: -0.1700

Data Index: 4257210 (Open Web Text)

Max Activating Token Index: 375

Text #18

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.3686. Min Act: -0.1700

Data Index: 6568929 (Open Web Text)

Max Activating Token Index: 685

Text #19

Max Range: 3.5024. Min Range: -3.5024

Max Act: 3.3379. Min Act: -0.1700

Data Index: 2666289 (Open Web Text)

Max Activating Token Index: 735