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

Dataset: Open Web Text

Neuron 1614 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: 4.0068. Min Range: -4.0068

Max Act: 4.0068. Min Act: -0.1700

Data Index: 6864028 (Open Web Text)

Max Activating Token Index: 91

Text #1

Max Range: 4.0068. Min Range: -4.0068

Max Act: 3.9782. Min Act: -0.1700

Data Index: 8419527 (Open Web Text)

Max Activating Token Index: 455

Text #2

Max Range: 4.0068. Min Range: -4.0068

Max Act: 3.8201. Min Act: -0.1700

Data Index: 4702741 (Open Web Text)

Max Activating Token Index: 269

Text #3

Max Range: 4.0068. Min Range: -4.0068

Max Act: 3.7903. Min Act: -0.1700

Data Index: 7168172 (Open Web Text)

Max Activating Token Index: 341

Text #4

Max Range: 4.0068. Min Range: -4.0068

Max Act: 3.7930. Min Act: -0.1700

Data Index: 4702744 (Open Web Text)

Max Activating Token Index: 438

Text #5

Max Range: 4.0068. Min Range: -4.0068

Max Act: 3.7488. Min Act: -0.1700

Data Index: 1381260 (Open Web Text)

Max Activating Token Index: 721

Text #6

Max Range: 4.0068. Min Range: -4.0068

Max Act: 3.7461. Min Act: -0.1700

Data Index: 8344414 (Open Web Text)

Max Activating Token Index: 52

Text #7

Max Range: 4.0068. Min Range: -4.0068

Max Act: 3.7617. Min Act: -0.1700

Data Index: 5635506 (Open Web Text)

Max Activating Token Index: 720

Text #8

Max Range: 4.0068. Min Range: -4.0068

Max Act: 3.6920. Min Act: -0.1700

Data Index: 3809937 (Open Web Text)

Max Activating Token Index: 720

Text #9

Max Range: 4.0068. Min Range: -4.0068

Max Act: 3.7044. Min Act: -0.1700

Data Index: 5155223 (Open Web Text)

Max Activating Token Index: 892

Text #10

Max Range: 4.0068. Min Range: -4.0068

Max Act: 3.7209. Min Act: -0.1700

Data Index: 3136749 (Open Web Text)

Max Activating Token Index: 395

Text #11

Max Range: 4.0068. Min Range: -4.0068

Max Act: 3.7192. Min Act: -0.1700

Data Index: 1676829 (Open Web Text)

Max Activating Token Index: 377

Text #12

Max Range: 4.0068. Min Range: -4.0068

Max Act: 3.6864. Min Act: -0.1700

Data Index: 5635502 (Open Web Text)

Max Activating Token Index: 936

Text #13

Max Range: 4.0068. Min Range: -4.0068

Max Act: 3.7063. Min Act: -0.1700

Data Index: 8549142 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 4.0068. Min Range: -4.0068

Max Act: 3.6921. Min Act: -0.1700

Data Index: 3104438 (Open Web Text)

Max Activating Token Index: 595

Text #15

Max Range: 4.0068. Min Range: -4.0068

Max Act: 3.6653. Min Act: -0.1700

Data Index: 4274897 (Open Web Text)

Max Activating Token Index: 972

Text #16

Max Range: 4.0068. Min Range: -4.0068

Max Act: 3.6637. Min Act: -0.1700

Data Index: 5831047 (Open Web Text)

Max Activating Token Index: 758

Text #17

Max Range: 4.0068. Min Range: -4.0068

Max Act: 3.6765. Min Act: -0.1700

Data Index: 5158114 (Open Web Text)

Max Activating Token Index: 201

Text #18

Max Range: 4.0068. Min Range: -4.0068

Max Act: 3.7060. Min Act: -0.1700

Data Index: 4599573 (Open Web Text)

Max Activating Token Index: 173

Text #19

Max Range: 4.0068. Min Range: -4.0068

Max Act: 3.6542. Min Act: -0.1700

Data Index: 4754292 (Open Web Text)

Max Activating Token Index: 350