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

Dataset: Open Web Text

Neuron 438 in Layer 5

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: 4.7247. Min Range: -4.7247

Max Act: 4.7247. Min Act: -0.1700

Data Index: 6957109 (Open Web Text)

Max Activating Token Index: 112

Text #1

Max Range: 4.7247. Min Range: -4.7247

Max Act: 4.6937. Min Act: -0.1700

Data Index: 6957117 (Open Web Text)

Max Activating Token Index: 142

Text #2

Max Range: 4.7247. Min Range: -4.7247

Max Act: 4.6458. Min Act: -0.1700

Data Index: 5691437 (Open Web Text)

Max Activating Token Index: 321

Text #3

Max Range: 4.7247. Min Range: -4.7247

Max Act: 4.6386. Min Act: -0.1700

Data Index: 1417306 (Open Web Text)

Max Activating Token Index: 167

Text #4

Max Range: 4.7247. Min Range: -4.7247

Max Act: 4.6235. Min Act: -0.1700

Data Index: 5490203 (Open Web Text)

Max Activating Token Index: 47

Text #5

Max Range: 4.7247. Min Range: -4.7247

Max Act: 4.6106. Min Act: -0.1700

Data Index: 4845484 (Open Web Text)

Max Activating Token Index: 840

Text #6

Max Range: 4.7247. Min Range: -4.7247

Max Act: 4.5658. Min Act: -0.1700

Data Index: 2182683 (Open Web Text)

Max Activating Token Index: 726

Text #7

Max Range: 4.7247. Min Range: -4.7247

Max Act: 4.5846. Min Act: -0.1700

Data Index: 1392080 (Open Web Text)

Max Activating Token Index: 296

Text #8

Max Range: 4.7247. Min Range: -4.7247

Max Act: 4.5707. Min Act: -0.1700

Data Index: 7211120 (Open Web Text)

Max Activating Token Index: 262

Text #9

Max Range: 4.7247. Min Range: -4.7247

Max Act: 4.5390. Min Act: -0.1700

Data Index: 4505219 (Open Web Text)

Max Activating Token Index: 581

Text #10

Max Range: 4.7247. Min Range: -4.7247

Max Act: 4.5359. Min Act: -0.1700

Data Index: 2182688 (Open Web Text)

Max Activating Token Index: 19

Text #11

Max Range: 4.7247. Min Range: -4.7247

Max Act: 4.5601. Min Act: -0.1700

Data Index: 2220614 (Open Web Text)

Max Activating Token Index: 949

Text #12

Max Range: 4.7247. Min Range: -4.7247

Max Act: 4.5634. Min Act: -0.1700

Data Index: 2991688 (Open Web Text)

Max Activating Token Index: 748

Text #13

Max Range: 4.7247. Min Range: -4.7247

Max Act: 4.5179. Min Act: -0.1700

Data Index: 7732146 (Open Web Text)

Max Activating Token Index: 876

Text #14

Max Range: 4.7247. Min Range: -4.7247

Max Act: 4.4942. Min Act: -0.1700

Data Index: 751840 (Open Web Text)

Max Activating Token Index: 350

Text #15

Max Range: 4.7247. Min Range: -4.7247

Max Act: 4.5096. Min Act: -0.1700

Data Index: 8303356 (Open Web Text)

Max Activating Token Index: 610

Text #16

Max Range: 4.7247. Min Range: -4.7247

Max Act: 4.5034. Min Act: -0.1700

Data Index: 512630 (Open Web Text)

Max Activating Token Index: 334

Text #17

Max Range: 4.7247. Min Range: -4.7247

Max Act: 4.5246. Min Act: -0.1700

Data Index: 3355833 (Open Web Text)

Max Activating Token Index: 243

Text #18

Max Range: 4.7247. Min Range: -4.7247

Max Act: 4.4777. Min Act: -0.1700

Data Index: 2182687 (Open Web Text)

Max Activating Token Index: 101

Text #19

Max Range: 4.7247. Min Range: -4.7247

Max Act: 4.4766. Min Act: -0.1700

Data Index: 4572722 (Open Web Text)

Max Activating Token Index: 493