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

Dataset: Open Web Text

Neuron 98 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: 3.8660. Min Range: -3.8660

Max Act: 3.8660. Min Act: -0.1700

Data Index: 372657 (Open Web Text)

Max Activating Token Index: 149

Text #1

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.8043. Min Act: -0.1700

Data Index: 6439440 (Open Web Text)

Max Activating Token Index: 124

Text #2

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.6714. Min Act: -0.1700

Data Index: 7282165 (Open Web Text)

Max Activating Token Index: 321

Text #3

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.5925. Min Act: -0.1700

Data Index: 7589800 (Open Web Text)

Max Activating Token Index: 590

Text #4

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.5508. Min Act: -0.1700

Data Index: 444250 (Open Web Text)

Max Activating Token Index: 40

Text #5

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.5462. Min Act: -0.1700

Data Index: 3271840 (Open Web Text)

Max Activating Token Index: 675

Text #6

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.5029. Min Act: -0.1700

Data Index: 1312964 (Open Web Text)

Max Activating Token Index: 172

Text #7

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.4598. Min Act: -0.1700

Data Index: 7305768 (Open Web Text)

Max Activating Token Index: 70

Text #8

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.4548. Min Act: -0.1700

Data Index: 4857357 (Open Web Text)

Max Activating Token Index: 630

Text #9

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.4392. Min Act: -0.1700

Data Index: 6091195 (Open Web Text)

Max Activating Token Index: 557

Text #10

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.4450. Min Act: -0.1700

Data Index: 4304303 (Open Web Text)

Max Activating Token Index: 45

Text #11

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.4415. Min Act: -0.1700

Data Index: 7026156 (Open Web Text)

Max Activating Token Index: 610

Text #12

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.4431. Min Act: -0.1700

Data Index: 3574265 (Open Web Text)

Max Activating Token Index: 121

Text #13

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.4261. Min Act: -0.1700

Data Index: 6727476 (Open Web Text)

Max Activating Token Index: 192

Text #14

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.4423. Min Act: -0.1700

Data Index: 4757698 (Open Web Text)

Max Activating Token Index: 510

Text #15

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.4310. Min Act: -0.1700

Data Index: 6565611 (Open Web Text)

Max Activating Token Index: 721

Text #16

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.4500. Min Act: -0.1700

Data Index: 3278386 (Open Web Text)

Max Activating Token Index: 603

Text #17

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.4094. Min Act: -0.1700

Data Index: 124732 (Open Web Text)

Max Activating Token Index: 229

Text #18

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.4196. Min Act: -0.1700

Data Index: 3498702 (Open Web Text)

Max Activating Token Index: 437

Text #19

Max Range: 3.8660. Min Range: -3.8660

Max Act: 3.4109. Min Act: -0.1700

Data Index: 5338166 (Open Web Text)

Max Activating Token Index: 245