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

Dataset: Open Web Text

Neuron 1533 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: 3.1769. Min Range: -3.1769

Max Act: 3.1769. Min Act: -0.1700

Data Index: 4959255 (Open Web Text)

Max Activating Token Index: 100

Text #1

Max Range: 3.1769. Min Range: -3.1769

Max Act: 3.0073. Min Act: -0.1700

Data Index: 5896282 (Open Web Text)

Max Activating Token Index: 61

Text #2

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.9642. Min Act: -0.1700

Data Index: 2473705 (Open Web Text)

Max Activating Token Index: 80

Text #3

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.9275. Min Act: -0.1700

Data Index: 4094934 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.9367. Min Act: -0.1700

Data Index: 6421428 (Open Web Text)

Max Activating Token Index: 55

Text #5

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.9328. Min Act: -0.1700

Data Index: 5796389 (Open Web Text)

Max Activating Token Index: 74

Text #6

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.9218. Min Act: -0.1700

Data Index: 732645 (Open Web Text)

Max Activating Token Index: 95

Text #7

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.9097. Min Act: -0.1700

Data Index: 2874860 (Open Web Text)

Max Activating Token Index: 56

Text #8

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.9076. Min Act: -0.1700

Data Index: 8212650 (Open Web Text)

Max Activating Token Index: 133

Text #9

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.8704. Min Act: -0.1700

Data Index: 4771022 (Open Web Text)

Max Activating Token Index: 32

Text #10

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.8517. Min Act: -0.1700

Data Index: 4446963 (Open Web Text)

Max Activating Token Index: 184

Text #11

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.8160. Min Act: -0.1700

Data Index: 6145141 (Open Web Text)

Max Activating Token Index: 60

Text #12

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.8023. Min Act: -0.1700

Data Index: 4377309 (Open Web Text)

Max Activating Token Index: 64

Text #13

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.7502. Min Act: -0.1700

Data Index: 4267525 (Open Web Text)

Max Activating Token Index: 69

Text #14

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.7716. Min Act: -0.1700

Data Index: 2512014 (Open Web Text)

Max Activating Token Index: 54

Text #15

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.7443. Min Act: -0.1700

Data Index: 6734246 (Open Web Text)

Max Activating Token Index: 91

Text #16

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.7285. Min Act: -0.1700

Data Index: 1632559 (Open Web Text)

Max Activating Token Index: 115

Text #17

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.7254. Min Act: -0.1700

Data Index: 444910 (Open Web Text)

Max Activating Token Index: 925

Text #18

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.7271. Min Act: -0.1700

Data Index: 4390417 (Open Web Text)

Max Activating Token Index: 800

Text #19

Max Range: 3.1769. Min Range: -3.1769

Max Act: 2.7784. Min Act: -0.1700

Data Index: 3936937 (Open Web Text)

Max Activating Token Index: 1023