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

Dataset: Open Web Text

Neuron 223 in Layer 4

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: 4.3651. Min Range: -4.3651

Max Act: 4.3651. Min Act: -0.1700

Data Index: 82908 (Open Web Text)

Max Activating Token Index: 425

Text #1

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.2575. Min Act: -0.1700

Data Index: 7075050 (Open Web Text)

Max Activating Token Index: 362

Text #2

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.2746. Min Act: -0.1700

Data Index: 6420067 (Open Web Text)

Max Activating Token Index: 243

Text #3

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.2466. Min Act: -0.1700

Data Index: 5254047 (Open Web Text)

Max Activating Token Index: 743

Text #4

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.2210. Min Act: -0.1700

Data Index: 1536580 (Open Web Text)

Max Activating Token Index: 1020

Text #5

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.1599. Min Act: -0.1700

Data Index: 6170455 (Open Web Text)

Max Activating Token Index: 358

Text #6

Max Range: 4.3651. Min Range: -4.3651

Max Act: 4.0764. Min Act: -0.1700

Data Index: 1065305 (Open Web Text)

Max Activating Token Index: 240

Text #7

Max Range: 4.3651. Min Range: -4.3651

Max Act: 3.9600. Min Act: -0.1700

Data Index: 4751626 (Open Web Text)

Max Activating Token Index: 951

Text #8

Max Range: 4.3651. Min Range: -4.3651

Max Act: 3.9411. Min Act: -0.1700

Data Index: 6601979 (Open Web Text)

Max Activating Token Index: 369

Text #9

Max Range: 4.3651. Min Range: -4.3651

Max Act: 3.9769. Min Act: -0.1700

Data Index: 3160061 (Open Web Text)

Max Activating Token Index: 164

Text #10

Max Range: 4.3651. Min Range: -4.3651

Max Act: 3.9647. Min Act: -0.1700

Data Index: 3233737 (Open Web Text)

Max Activating Token Index: 285

Text #11

Max Range: 4.3651. Min Range: -4.3651

Max Act: 3.9719. Min Act: -0.1700

Data Index: 1556362 (Open Web Text)

Max Activating Token Index: 944

Text #12

Max Range: 4.3651. Min Range: -4.3651

Max Act: 3.9219. Min Act: -0.1700

Data Index: 2018791 (Open Web Text)

Max Activating Token Index: 574

Text #13

Max Range: 4.3651. Min Range: -4.3651

Max Act: 3.9218. Min Act: -0.1700

Data Index: 2064164 (Open Web Text)

Max Activating Token Index: 518

Text #14

Max Range: 4.3651. Min Range: -4.3651

Max Act: 3.9408. Min Act: -0.1700

Data Index: 3963265 (Open Web Text)

Max Activating Token Index: 59

Text #15

Max Range: 4.3651. Min Range: -4.3651

Max Act: 3.9338. Min Act: -0.1700

Data Index: 972050 (Open Web Text)

Max Activating Token Index: 886

Text #16

Max Range: 4.3651. Min Range: -4.3651

Max Act: 3.9537. Min Act: -0.1700

Data Index: 8056435 (Open Web Text)

Max Activating Token Index: 539

Text #17

Max Range: 4.3651. Min Range: -4.3651

Max Act: 3.9033. Min Act: -0.1700

Data Index: 4577832 (Open Web Text)

Max Activating Token Index: 537

Text #18

Max Range: 4.3651. Min Range: -4.3651

Max Act: 3.9075. Min Act: -0.1700

Data Index: 4521870 (Open Web Text)

Max Activating Token Index: 164

Text #19

Max Range: 4.3651. Min Range: -4.3651

Max Act: 3.8986. Min Act: -0.1700

Data Index: 2806311 (Open Web Text)

Max Activating Token Index: 26