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

Dataset: Open Web Text

Neuron 839 in Layer 6

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: 3.0975. Min Range: -3.0975

Max Act: 3.0975. Min Act: -0.1700

Data Index: 5910585 (Open Web Text)

Max Activating Token Index: 678

Text #1

Max Range: 3.0975. Min Range: -3.0975

Max Act: 3.0786. Min Act: -0.1700

Data Index: 6617656 (Open Web Text)

Max Activating Token Index: 788

Text #2

Max Range: 3.0975. Min Range: -3.0975

Max Act: 3.0152. Min Act: -0.1700

Data Index: 8212846 (Open Web Text)

Max Activating Token Index: 602

Text #3

Max Range: 3.0975. Min Range: -3.0975

Max Act: 2.9965. Min Act: -0.1700

Data Index: 777807 (Open Web Text)

Max Activating Token Index: 260

Text #4

Max Range: 3.0975. Min Range: -3.0975

Max Act: 3.0148. Min Act: -0.1700

Data Index: 4976792 (Open Web Text)

Max Activating Token Index: 684

Text #5

Max Range: 3.0975. Min Range: -3.0975

Max Act: 2.9931. Min Act: -0.1700

Data Index: 5975728 (Open Web Text)

Max Activating Token Index: 967

Text #6

Max Range: 3.0975. Min Range: -3.0975

Max Act: 2.9794. Min Act: -0.1700

Data Index: 2328168 (Open Web Text)

Max Activating Token Index: 200

Text #7

Max Range: 3.0975. Min Range: -3.0975

Max Act: 2.9505. Min Act: -0.1700

Data Index: 1533080 (Open Web Text)

Max Activating Token Index: 478

Text #8

Max Range: 3.0975. Min Range: -3.0975

Max Act: 2.9568. Min Act: -0.1700

Data Index: 8385156 (Open Web Text)

Max Activating Token Index: 667

Text #9

Max Range: 3.0975. Min Range: -3.0975

Max Act: 2.9729. Min Act: -0.1700

Data Index: 1114870 (Open Web Text)

Max Activating Token Index: 913

Text #10

Max Range: 3.0975. Min Range: -3.0975

Max Act: 2.9504. Min Act: -0.1700

Data Index: 283745 (Open Web Text)

Max Activating Token Index: 231

Text #11

Max Range: 3.0975. Min Range: -3.0975

Max Act: 2.9445. Min Act: -0.1700

Data Index: 3385223 (Open Web Text)

Max Activating Token Index: 181

Text #12

Max Range: 3.0975. Min Range: -3.0975

Max Act: 2.9253. Min Act: -0.1700

Data Index: 5626130 (Open Web Text)

Max Activating Token Index: 227

Text #13

Max Range: 3.0975. Min Range: -3.0975

Max Act: 2.9172. Min Act: -0.1700

Data Index: 5785572 (Open Web Text)

Max Activating Token Index: 708

Text #14

Max Range: 3.0975. Min Range: -3.0975

Max Act: 2.9023. Min Act: -0.1700

Data Index: 6892764 (Open Web Text)

Max Activating Token Index: 674

Text #15

Max Range: 3.0975. Min Range: -3.0975

Max Act: 2.9171. Min Act: -0.1700

Data Index: 7588564 (Open Web Text)

Max Activating Token Index: 890

Text #16

Max Range: 3.0975. Min Range: -3.0975

Max Act: 2.8901. Min Act: -0.1700

Data Index: 1910355 (Open Web Text)

Max Activating Token Index: 451

Text #17

Max Range: 3.0975. Min Range: -3.0975

Max Act: 2.9358. Min Act: -0.1700

Data Index: 7454094 (Open Web Text)

Max Activating Token Index: 583

Text #18

Max Range: 3.0975. Min Range: -3.0975

Max Act: 2.9119. Min Act: -0.1700

Data Index: 639298 (Open Web Text)

Max Activating Token Index: 724

Text #19

Max Range: 3.0975. Min Range: -3.0975

Max Act: 2.8740. Min Act: -0.1700

Data Index: 3553268 (Open Web Text)

Max Activating Token Index: 717