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

Dataset: Open Web Text

Neuron 400 in Layer 2

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: 3.1700. Min Range: -3.1700

Max Act: 3.1507. Min Act: -0.1700

Data Index: 1269412 (Open Web Text)

Max Activating Token Index: 96

Text #1

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.1694. Min Act: -0.1700

Data Index: 5328014 (Open Web Text)

Max Activating Token Index: 494

Text #2

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.1700. Min Act: -0.1700

Data Index: 6029671 (Open Web Text)

Max Activating Token Index: 136

Text #3

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.1561. Min Act: -0.1700

Data Index: 2280214 (Open Web Text)

Max Activating Token Index: 145

Text #4

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.1227. Min Act: -0.1700

Data Index: 5863539 (Open Web Text)

Max Activating Token Index: 224

Text #5

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.1288. Min Act: -0.1700

Data Index: 2675695 (Open Web Text)

Max Activating Token Index: 126

Text #6

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.1118. Min Act: -0.1700

Data Index: 3687765 (Open Web Text)

Max Activating Token Index: 431

Text #7

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.1293. Min Act: -0.1700

Data Index: 6146778 (Open Web Text)

Max Activating Token Index: 686

Text #8

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.1159. Min Act: -0.1700

Data Index: 2753733 (Open Web Text)

Max Activating Token Index: 481

Text #9

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.1206. Min Act: -0.1700

Data Index: 104070 (Open Web Text)

Max Activating Token Index: 471

Text #10

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.0886. Min Act: -0.1700

Data Index: 2509608 (Open Web Text)

Max Activating Token Index: 293

Text #11

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.1088. Min Act: -0.1700

Data Index: 8812190 (Open Web Text)

Max Activating Token Index: 940

Text #12

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.1106. Min Act: -0.1700

Data Index: 8778345 (Open Web Text)

Max Activating Token Index: 617

Text #13

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.0874. Min Act: -0.1700

Data Index: 6815956 (Open Web Text)

Max Activating Token Index: 144

Text #14

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.0876. Min Act: -0.1700

Data Index: 7179000 (Open Web Text)

Max Activating Token Index: 345

Text #15

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.0729. Min Act: -0.1700

Data Index: 3131521 (Open Web Text)

Max Activating Token Index: 80

Text #16

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.0796. Min Act: -0.1700

Data Index: 6570636 (Open Web Text)

Max Activating Token Index: 305

Text #17

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.0609. Min Act: -0.1700

Data Index: 5589979 (Open Web Text)

Max Activating Token Index: 129

Text #18

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.0803. Min Act: -0.1700

Data Index: 4907190 (Open Web Text)

Max Activating Token Index: 731

Text #19

Max Range: 3.1700. Min Range: -3.1700

Max Act: 3.0518. Min Act: -0.1700

Data Index: 5452370 (Open Web Text)

Max Activating Token Index: 24