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

Dataset: Open Web Text

Neuron 2085 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: 3.7970. Min Range: -3.7970

Max Act: 3.7970. Min Act: -0.1700

Data Index: 1099250 (Open Web Text)

Max Activating Token Index: 87

Text #1

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.6506. Min Act: -0.1700

Data Index: 6153506 (Open Web Text)

Max Activating Token Index: 117

Text #2

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.6047. Min Act: -0.1700

Data Index: 705571 (Open Web Text)

Max Activating Token Index: 267

Text #3

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.6033. Min Act: -0.1700

Data Index: 5746614 (Open Web Text)

Max Activating Token Index: 123

Text #4

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.6045. Min Act: -0.1700

Data Index: 1112614 (Open Web Text)

Max Activating Token Index: 128

Text #5

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.5702. Min Act: -0.1700

Data Index: 7531624 (Open Web Text)

Max Activating Token Index: 781

Text #6

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.5495. Min Act: -0.1700

Data Index: 3927298 (Open Web Text)

Max Activating Token Index: 452

Text #7

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.5568. Min Act: -0.1700

Data Index: 1492099 (Open Web Text)

Max Activating Token Index: 491

Text #8

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.5324. Min Act: -0.1700

Data Index: 5183968 (Open Web Text)

Max Activating Token Index: 221

Text #9

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.5113. Min Act: -0.1700

Data Index: 8002724 (Open Web Text)

Max Activating Token Index: 730

Text #10

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.5058. Min Act: -0.1700

Data Index: 6082732 (Open Web Text)

Max Activating Token Index: 775

Text #11

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.5207. Min Act: -0.1700

Data Index: 2040447 (Open Web Text)

Max Activating Token Index: 286

Text #12

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.4949. Min Act: -0.1700

Data Index: 6305128 (Open Web Text)

Max Activating Token Index: 986

Text #13

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.4858. Min Act: -0.1700

Data Index: 8114843 (Open Web Text)

Max Activating Token Index: 860

Text #14

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.4885. Min Act: -0.1700

Data Index: 3848284 (Open Web Text)

Max Activating Token Index: 975

Text #15

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.4686. Min Act: -0.1700

Data Index: 1526724 (Open Web Text)

Max Activating Token Index: 26

Text #16

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.4707. Min Act: -0.1700

Data Index: 1260064 (Open Web Text)

Max Activating Token Index: 211

Text #17

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.4465. Min Act: -0.1700

Data Index: 2963311 (Open Web Text)

Max Activating Token Index: 205

Text #18

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.4373. Min Act: -0.1700

Data Index: 6258483 (Open Web Text)

Max Activating Token Index: 943

Text #19

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.4422. Min Act: -0.1700

Data Index: 785147 (Open Web Text)

Max Activating Token Index: 631