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

Dataset: Open Web Text

Neuron 2555 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: 2.4756. Min Range: -2.4756

Max Act: 2.4661. Min Act: -0.1700

Data Index: 8636685 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 2.4756. Min Range: -2.4756

Max Act: 2.4756. Min Act: -0.1700

Data Index: 6935959 (Open Web Text)

Max Activating Token Index: 20

Text #2

Max Range: 2.4756. Min Range: -2.4756

Max Act: 2.4530. Min Act: -0.1700

Data Index: 1281908 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 2.4756. Min Range: -2.4756

Max Act: 2.4628. Min Act: -0.1700

Data Index: 840802 (Open Web Text)

Max Activating Token Index: 235

Text #4

Max Range: 2.4756. Min Range: -2.4756

Max Act: 2.4544. Min Act: -0.1700

Data Index: 7619951 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.4756. Min Range: -2.4756

Max Act: 2.4639. Min Act: -0.1700

Data Index: 4560111 (Open Web Text)

Max Activating Token Index: 66

Text #6

Max Range: 2.4756. Min Range: -2.4756

Max Act: 2.4407. Min Act: -0.1700

Data Index: 3098144 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.4756. Min Range: -2.4756

Max Act: 2.4275. Min Act: -0.1700

Data Index: 7947726 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.4756. Min Range: -2.4756

Max Act: 2.4216. Min Act: -0.1700

Data Index: 6569368 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 2.4756. Min Range: -2.4756

Max Act: 2.4268. Min Act: -0.1700

Data Index: 2227652 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.4756. Min Range: -2.4756

Max Act: 2.4267. Min Act: -0.1700

Data Index: 3279918 (Open Web Text)

Max Activating Token Index: 144

Text #11

Max Range: 2.4756. Min Range: -2.4756

Max Act: 2.4230. Min Act: -0.1700

Data Index: 3479572 (Open Web Text)

Max Activating Token Index: 66

Text #12

Max Range: 2.4756. Min Range: -2.4756

Max Act: 2.3854. Min Act: -0.1700

Data Index: 3735761 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.4756. Min Range: -2.4756

Max Act: 2.4186. Min Act: -0.1700

Data Index: 2498379 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 2.4756. Min Range: -2.4756

Max Act: 2.3962. Min Act: -0.1700

Data Index: 1719435 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.4756. Min Range: -2.4756

Max Act: 2.4081. Min Act: -0.1700

Data Index: 2217683 (Open Web Text)

Max Activating Token Index: 505

Text #16

Max Range: 2.4756. Min Range: -2.4756

Max Act: 2.3965. Min Act: -0.1700

Data Index: 3360576 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.4756. Min Range: -2.4756

Max Act: 2.4100. Min Act: -0.1700

Data Index: 6291885 (Open Web Text)

Max Activating Token Index: 20

Text #18

Max Range: 2.4756. Min Range: -2.4756

Max Act: 2.3941. Min Act: -0.1700

Data Index: 3571151 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.4756. Min Range: -2.4756

Max Act: 2.3925. Min Act: -0.1700

Data Index: 1265496 (Open Web Text)

Max Activating Token Index: 132