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

Dataset: Open Web Text

Neuron 3044 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: 1.8391. Min Range: -1.8391

Max Act: 1.8391. Min Act: -0.1700

Data Index: 2030223 (Open Web Text)

Max Activating Token Index: 63

Text #1

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.7911. Min Act: -0.1700

Data Index: 8755193 (Open Web Text)

Max Activating Token Index: 94

Text #2

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.7935. Min Act: -0.1700

Data Index: 3888783 (Open Web Text)

Max Activating Token Index: 188

Text #3

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.7742. Min Act: -0.1700

Data Index: 8041110 (Open Web Text)

Max Activating Token Index: 71

Text #4

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.7615. Min Act: -0.1700

Data Index: 2826638 (Open Web Text)

Max Activating Token Index: 24

Text #5

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.7584. Min Act: -0.1700

Data Index: 6133337 (Open Web Text)

Max Activating Token Index: 20

Text #6

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.7501. Min Act: -0.1699

Data Index: 4151274 (Open Web Text)

Max Activating Token Index: 67

Text #7

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.7401. Min Act: -0.1700

Data Index: 1223722 (Open Web Text)

Max Activating Token Index: 265

Text #8

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.7329. Min Act: -0.1700

Data Index: 3720906 (Open Web Text)

Max Activating Token Index: 112

Text #9

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.7323. Min Act: -0.1700

Data Index: 4674270 (Open Web Text)

Max Activating Token Index: 516

Text #10

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.7214. Min Act: -0.1700

Data Index: 6244838 (Open Web Text)

Max Activating Token Index: 70

Text #11

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.7246. Min Act: -0.1700

Data Index: 1820746 (Open Web Text)

Max Activating Token Index: 94

Text #12

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.7238. Min Act: -0.1700

Data Index: 5725045 (Open Web Text)

Max Activating Token Index: 534

Text #13

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.7186. Min Act: -0.1700

Data Index: 2551414 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.7198. Min Act: -0.1700

Data Index: 3297958 (Open Web Text)

Max Activating Token Index: 12

Text #15

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.7259. Min Act: -0.1700

Data Index: 6043080 (Open Web Text)

Max Activating Token Index: 366

Text #16

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.7182. Min Act: -0.1700

Data Index: 4198112 (Open Web Text)

Max Activating Token Index: 188

Text #17

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.7150. Min Act: -0.1700

Data Index: 1889830 (Open Web Text)

Max Activating Token Index: 523

Text #18

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.7104. Min Act: -0.1700

Data Index: 7610965 (Open Web Text)

Max Activating Token Index: 38

Text #19

Max Range: 1.8391. Min Range: -1.8391

Max Act: 1.7091. Min Act: -0.1700

Data Index: 4874690 (Open Web Text)

Max Activating Token Index: 205