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

Dataset: Open Web Text

Neuron 888 in Layer 0

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: 6.0369. Min Range: -6.0369

Max Act: 6.0369. Min Act: -0.1700

Data Index: 6936609 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 6.0369. Min Range: -6.0369

Max Act: 5.9471. Min Act: -0.1700

Data Index: 6574332 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 6.0369. Min Range: -6.0369

Max Act: 5.9441. Min Act: -0.1700

Data Index: 681537 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 6.0369. Min Range: -6.0369

Max Act: 5.8819. Min Act: -0.1700

Data Index: 1112670 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 6.0369. Min Range: -6.0369

Max Act: 5.8846. Min Act: -0.1700

Data Index: 3250673 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 6.0369. Min Range: -6.0369

Max Act: 5.9087. Min Act: -0.1700

Data Index: 5027248 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 6.0369. Min Range: -6.0369

Max Act: 5.8987. Min Act: -0.1700

Data Index: 7823652 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 6.0369. Min Range: -6.0369

Max Act: 5.8799. Min Act: -0.1700

Data Index: 4412010 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 6.0369. Min Range: -6.0369

Max Act: 5.8612. Min Act: -0.1700

Data Index: 6765214 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 6.0369. Min Range: -6.0369

Max Act: 5.8825. Min Act: -0.1700

Data Index: 3595330 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 6.0369. Min Range: -6.0369

Max Act: 5.8641. Min Act: -0.1700

Data Index: 3554575 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 6.0369. Min Range: -6.0369

Max Act: 5.8544. Min Act: -0.1700

Data Index: 2268288 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 6.0369. Min Range: -6.0369

Max Act: 5.8865. Min Act: -0.1700

Data Index: 3504781 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 6.0369. Min Range: -6.0369

Max Act: 5.8726. Min Act: -0.1700

Data Index: 6052323 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 6.0369. Min Range: -6.0369

Max Act: 5.8663. Min Act: -0.1700

Data Index: 5586919 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 6.0369. Min Range: -6.0369

Max Act: 5.8664. Min Act: -0.1700

Data Index: 8353889 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 6.0369. Min Range: -6.0369

Max Act: 5.8413. Min Act: -0.1700

Data Index: 2262975 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 6.0369. Min Range: -6.0369

Max Act: 5.8313. Min Act: -0.1700

Data Index: 7785748 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 6.0369. Min Range: -6.0369

Max Act: 5.8476. Min Act: -0.1700

Data Index: 8049662 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 6.0369. Min Range: -6.0369

Max Act: 5.8544. Min Act: -0.1700

Data Index: 2094235 (Open Web Text)

Max Activating Token Index: 4