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

Dataset: Open Web Text

Neuron 1271 in Layer 1

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: 1.4315. Min Range: -1.4315

Max Act: 1.4315. Min Act: -0.1700

Data Index: 8229979 (Open Web Text)

Max Activating Token Index: 20

Text #1

Max Range: 1.4315. Min Range: -1.4315

Max Act: 1.4213. Min Act: -0.1700

Data Index: 8229997 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 1.4315. Min Range: -1.4315

Max Act: 1.4144. Min Act: -0.1700

Data Index: 8230007 (Open Web Text)

Max Activating Token Index: 21

Text #3

Max Range: 1.4315. Min Range: -1.4315

Max Act: 1.4209. Min Act: -0.1700

Data Index: 8230004 (Open Web Text)

Max Activating Token Index: 16

Text #4

Max Range: 1.4315. Min Range: -1.4315

Max Act: 1.3974. Min Act: -0.1700

Data Index: 8230002 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 1.4315. Min Range: -1.4315

Max Act: 1.3334. Min Act: -0.1700

Data Index: 7195956 (Open Web Text)

Max Activating Token Index: 23

Text #6

Max Range: 1.4315. Min Range: -1.4315

Max Act: 1.3342. Min Act: -0.1700

Data Index: 5586163 (Open Web Text)

Max Activating Token Index: 23

Text #7

Max Range: 1.4315. Min Range: -1.4315

Max Act: 1.3291. Min Act: -0.1700

Data Index: 7291421 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 1.4315. Min Range: -1.4315

Max Act: 1.3434. Min Act: -0.1700

Data Index: 8230005 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 1.4315. Min Range: -1.4315

Max Act: 1.3269. Min Act: -0.1700

Data Index: 3688679 (Open Web Text)

Max Activating Token Index: 23

Text #10

Max Range: 1.4315. Min Range: -1.4315

Max Act: 1.3301. Min Act: -0.1700

Data Index: 8003781 (Open Web Text)

Max Activating Token Index: 22

Text #11

Max Range: 1.4315. Min Range: -1.4315

Max Act: 1.3152. Min Act: -0.1700

Data Index: 4230000 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 1.4315. Min Range: -1.4315

Max Act: 1.3199. Min Act: -0.1700

Data Index: 2918209 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 1.4315. Min Range: -1.4315

Max Act: 1.3186. Min Act: -0.1700

Data Index: 5137582 (Open Web Text)

Max Activating Token Index: 22

Text #14

Max Range: 1.4315. Min Range: -1.4315

Max Act: 1.3206. Min Act: -0.1700

Data Index: 8230000 (Open Web Text)

Max Activating Token Index: 23

Text #15

Max Range: 1.4315. Min Range: -1.4315

Max Act: 1.3148. Min Act: -0.1700

Data Index: 4954007 (Open Web Text)

Max Activating Token Index: 20

Text #16

Max Range: 1.4315. Min Range: -1.4315

Max Act: 1.3091. Min Act: -0.1700

Data Index: 7346159 (Open Web Text)

Max Activating Token Index: 24

Text #17

Max Range: 1.4315. Min Range: -1.4315

Max Act: 1.3029. Min Act: -0.1700

Data Index: 706640 (Open Web Text)

Max Activating Token Index: 24

Text #18

Max Range: 1.4315. Min Range: -1.4315

Max Act: 1.3043. Min Act: -0.1700

Data Index: 5415790 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 1.4315. Min Range: -1.4315

Max Act: 1.2990. Min Act: -0.1700

Data Index: 5013157 (Open Web Text)

Max Activating Token Index: 20