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

Dataset: Open Web Text

Neuron 2226 in Layer 5

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: 4.6949. Min Range: -4.6949

Max Act: 4.6915. Min Act: -0.1700

Data Index: 5996415 (Open Web Text)

Max Activating Token Index: 454

Text #1

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.6640. Min Act: -0.1700

Data Index: 4831416 (Open Web Text)

Max Activating Token Index: 603

Text #2

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.6599. Min Act: -0.1700

Data Index: 6209272 (Open Web Text)

Max Activating Token Index: 235

Text #3

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.6949. Min Act: -0.1700

Data Index: 6555559 (Open Web Text)

Max Activating Token Index: 450

Text #4

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5941. Min Act: -0.1700

Data Index: 8143620 (Open Web Text)

Max Activating Token Index: 746

Text #5

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.6515. Min Act: -0.1700

Data Index: 2304334 (Open Web Text)

Max Activating Token Index: 324

Text #6

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.6047. Min Act: -0.1700

Data Index: 1407416 (Open Web Text)

Max Activating Token Index: 604

Text #7

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.6156. Min Act: -0.1700

Data Index: 7552414 (Open Web Text)

Max Activating Token Index: 444

Text #8

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5808. Min Act: -0.1700

Data Index: 679665 (Open Web Text)

Max Activating Token Index: 330

Text #9

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.6134. Min Act: -0.1700

Data Index: 2239671 (Open Web Text)

Max Activating Token Index: 456

Text #10

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5533. Min Act: -0.1700

Data Index: 8150626 (Open Web Text)

Max Activating Token Index: 745

Text #11

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5761. Min Act: -0.1700

Data Index: 1985388 (Open Web Text)

Max Activating Token Index: 671

Text #12

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5879. Min Act: -0.1700

Data Index: 1587656 (Open Web Text)

Max Activating Token Index: 847

Text #13

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5103. Min Act: -0.1700

Data Index: 6688098 (Open Web Text)

Max Activating Token Index: 755

Text #14

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5660. Min Act: -0.1700

Data Index: 4369004 (Open Web Text)

Max Activating Token Index: 434

Text #15

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5723. Min Act: -0.1700

Data Index: 1510232 (Open Web Text)

Max Activating Token Index: 907

Text #16

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5545. Min Act: -0.1700

Data Index: 6799203 (Open Web Text)

Max Activating Token Index: 144

Text #17

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5873. Min Act: -0.1700

Data Index: 1513807 (Open Web Text)

Max Activating Token Index: 570

Text #18

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5616. Min Act: -0.1700

Data Index: 7298335 (Open Web Text)

Max Activating Token Index: 811

Text #19

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5787. Min Act: -0.1700

Data Index: 7390583 (Open Web Text)

Max Activating Token Index: 122