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

Dataset: Open Web Text

Neuron 222 in Layer 2

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: 2.5675. Min Range: -2.5675

Max Act: 2.5675. Min Act: -0.1700

Data Index: 3218000 (Open Web Text)

Max Activating Token Index: 203

Text #1

Max Range: 2.5675. Min Range: -2.5675

Max Act: 2.5610. Min Act: -0.1700

Data Index: 3819834 (Open Web Text)

Max Activating Token Index: 479

Text #2

Max Range: 2.5675. Min Range: -2.5675

Max Act: 2.5447. Min Act: -0.1700

Data Index: 7018838 (Open Web Text)

Max Activating Token Index: 482

Text #3

Max Range: 2.5675. Min Range: -2.5675

Max Act: 2.5221. Min Act: -0.1700

Data Index: 6894385 (Open Web Text)

Max Activating Token Index: 79

Text #4

Max Range: 2.5675. Min Range: -2.5675

Max Act: 2.5260. Min Act: -0.1700

Data Index: 6366685 (Open Web Text)

Max Activating Token Index: 183

Text #5

Max Range: 2.5675. Min Range: -2.5675

Max Act: 2.5185. Min Act: -0.1700

Data Index: 474582 (Open Web Text)

Max Activating Token Index: 86

Text #6

Max Range: 2.5675. Min Range: -2.5675

Max Act: 2.5124. Min Act: -0.1700

Data Index: 2962391 (Open Web Text)

Max Activating Token Index: 85

Text #7

Max Range: 2.5675. Min Range: -2.5675

Max Act: 2.5090. Min Act: -0.1700

Data Index: 8481075 (Open Web Text)

Max Activating Token Index: 64

Text #8

Max Range: 2.5675. Min Range: -2.5675

Max Act: 2.5110. Min Act: -0.1700

Data Index: 6737011 (Open Web Text)

Max Activating Token Index: 760

Text #9

Max Range: 2.5675. Min Range: -2.5675

Max Act: 2.4935. Min Act: -0.1700

Data Index: 98254 (Open Web Text)

Max Activating Token Index: 913

Text #10

Max Range: 2.5675. Min Range: -2.5675

Max Act: 2.4818. Min Act: -0.1700

Data Index: 1198646 (Open Web Text)

Max Activating Token Index: 128

Text #11

Max Range: 2.5675. Min Range: -2.5675

Max Act: 2.4763. Min Act: -0.1700

Data Index: 5925136 (Open Web Text)

Max Activating Token Index: 131

Text #12

Max Range: 2.5675. Min Range: -2.5675

Max Act: 2.4738. Min Act: -0.1700

Data Index: 3752019 (Open Web Text)

Max Activating Token Index: 806

Text #13

Max Range: 2.5675. Min Range: -2.5675

Max Act: 2.4546. Min Act: -0.1700

Data Index: 2463694 (Open Web Text)

Max Activating Token Index: 578

Text #14

Max Range: 2.5675. Min Range: -2.5675

Max Act: 2.4646. Min Act: -0.1700

Data Index: 7105143 (Open Web Text)

Max Activating Token Index: 762

Text #15

Max Range: 2.5675. Min Range: -2.5675

Max Act: 2.4440. Min Act: -0.1700

Data Index: 6235386 (Open Web Text)

Max Activating Token Index: 41

Text #16

Max Range: 2.5675. Min Range: -2.5675

Max Act: 2.4722. Min Act: -0.1700

Data Index: 5549480 (Open Web Text)

Max Activating Token Index: 547

Text #17

Max Range: 2.5675. Min Range: -2.5675

Max Act: 2.4487. Min Act: -0.1700

Data Index: 7005360 (Open Web Text)

Max Activating Token Index: 313

Text #18

Max Range: 2.5675. Min Range: -2.5675

Max Act: 2.4500. Min Act: -0.1700

Data Index: 5200446 (Open Web Text)

Max Activating Token Index: 17

Text #19

Max Range: 2.5675. Min Range: -2.5675

Max Act: 2.4499. Min Act: -0.1700

Data Index: 3271012 (Open Web Text)

Max Activating Token Index: 803