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

Dataset: Open Web Text

Neuron 815 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: 2.0605. Min Range: -2.0605

Max Act: 2.0561. Min Act: -0.1700

Data Index: 6823427 (Open Web Text)

Max Activating Token Index: 292

Text #1

Max Range: 2.0605. Min Range: -2.0605

Max Act: 2.0524. Min Act: -0.1700

Data Index: 364116 (Open Web Text)

Max Activating Token Index: 460

Text #2

Max Range: 2.0605. Min Range: -2.0605

Max Act: 2.0605. Min Act: -0.1700

Data Index: 8694594 (Open Web Text)

Max Activating Token Index: 253

Text #3

Max Range: 2.0605. Min Range: -2.0605

Max Act: 2.0389. Min Act: -0.1700

Data Index: 8047989 (Open Web Text)

Max Activating Token Index: 484

Text #4

Max Range: 2.0605. Min Range: -2.0605

Max Act: 2.0227. Min Act: -0.1700

Data Index: 8360021 (Open Web Text)

Max Activating Token Index: 150

Text #5

Max Range: 2.0605. Min Range: -2.0605

Max Act: 2.0230. Min Act: -0.1700

Data Index: 1091863 (Open Web Text)

Max Activating Token Index: 198

Text #6

Max Range: 2.0605. Min Range: -2.0605

Max Act: 2.0321. Min Act: -0.1700

Data Index: 4481038 (Open Web Text)

Max Activating Token Index: 679

Text #7

Max Range: 2.0605. Min Range: -2.0605

Max Act: 2.0152. Min Act: -0.1700

Data Index: 8566865 (Open Web Text)

Max Activating Token Index: 785

Text #8

Max Range: 2.0605. Min Range: -2.0605

Max Act: 2.0109. Min Act: -0.1700

Data Index: 1768976 (Open Web Text)

Max Activating Token Index: 397

Text #9

Max Range: 2.0605. Min Range: -2.0605

Max Act: 2.0135. Min Act: -0.1700

Data Index: 358809 (Open Web Text)

Max Activating Token Index: 336

Text #10

Max Range: 2.0605. Min Range: -2.0605

Max Act: 2.0147. Min Act: -0.1700

Data Index: 7539818 (Open Web Text)

Max Activating Token Index: 313

Text #11

Max Range: 2.0605. Min Range: -2.0605

Max Act: 2.0119. Min Act: -0.1700

Data Index: 190760 (Open Web Text)

Max Activating Token Index: 787

Text #12

Max Range: 2.0605. Min Range: -2.0605

Max Act: 2.0113. Min Act: -0.1700

Data Index: 3184537 (Open Web Text)

Max Activating Token Index: 851

Text #13

Max Range: 2.0605. Min Range: -2.0605

Max Act: 2.0114. Min Act: -0.1699

Data Index: 1095358 (Open Web Text)

Max Activating Token Index: 149

Text #14

Max Range: 2.0605. Min Range: -2.0605

Max Act: 2.0079. Min Act: -0.1700

Data Index: 5480943 (Open Web Text)

Max Activating Token Index: 227

Text #15

Max Range: 2.0605. Min Range: -2.0605

Max Act: 2.0038. Min Act: -0.1699

Data Index: 4106726 (Open Web Text)

Max Activating Token Index: 399

Text #16

Max Range: 2.0605. Min Range: -2.0605

Max Act: 2.0075. Min Act: -0.1700

Data Index: 1510987 (Open Web Text)

Max Activating Token Index: 679

Text #17

Max Range: 2.0605. Min Range: -2.0605

Max Act: 1.9964. Min Act: -0.1700

Data Index: 2152940 (Open Web Text)

Max Activating Token Index: 124

Text #18

Max Range: 2.0605. Min Range: -2.0605

Max Act: 1.9932. Min Act: -0.1700

Data Index: 7172075 (Open Web Text)

Max Activating Token Index: 88

Text #19

Max Range: 2.0605. Min Range: -2.0605

Max Act: 1.9968. Min Act: -0.1700

Data Index: 317047 (Open Web Text)

Max Activating Token Index: 484