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

Dataset: Open Web Text

Neuron 452 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: 3.7064. Min Range: -3.7064

Max Act: 3.7064. Min Act: -0.1700

Data Index: 7740453 (Open Web Text)

Max Activating Token Index: 50

Text #1

Max Range: 3.7064. Min Range: -3.7064

Max Act: 3.6670. Min Act: -0.1700

Data Index: 4817135 (Open Web Text)

Max Activating Token Index: 883

Text #2

Max Range: 3.7064. Min Range: -3.7064

Max Act: 3.6312. Min Act: -0.1700

Data Index: 3248394 (Open Web Text)

Max Activating Token Index: 142

Text #3

Max Range: 3.7064. Min Range: -3.7064

Max Act: 3.6401. Min Act: -0.1700

Data Index: 5438810 (Open Web Text)

Max Activating Token Index: 300

Text #4

Max Range: 3.7064. Min Range: -3.7064

Max Act: 3.6468. Min Act: -0.1700

Data Index: 7196064 (Open Web Text)

Max Activating Token Index: 842

Text #5

Max Range: 3.7064. Min Range: -3.7064

Max Act: 3.5734. Min Act: -0.1700

Data Index: 7257524 (Open Web Text)

Max Activating Token Index: 350

Text #6

Max Range: 3.7064. Min Range: -3.7064

Max Act: 3.5548. Min Act: -0.1700

Data Index: 586916 (Open Web Text)

Max Activating Token Index: 715

Text #7

Max Range: 3.7064. Min Range: -3.7064

Max Act: 3.5425. Min Act: -0.1700

Data Index: 2858918 (Open Web Text)

Max Activating Token Index: 489

Text #8

Max Range: 3.7064. Min Range: -3.7064

Max Act: 3.5388. Min Act: -0.1700

Data Index: 8097816 (Open Web Text)

Max Activating Token Index: 331

Text #9

Max Range: 3.7064. Min Range: -3.7064

Max Act: 3.5202. Min Act: -0.1700

Data Index: 7200400 (Open Web Text)

Max Activating Token Index: 216

Text #10

Max Range: 3.7064. Min Range: -3.7064

Max Act: 3.5003. Min Act: -0.1700

Data Index: 3651637 (Open Web Text)

Max Activating Token Index: 769

Text #11

Max Range: 3.7064. Min Range: -3.7064

Max Act: 3.5330. Min Act: -0.1700

Data Index: 3917538 (Open Web Text)

Max Activating Token Index: 929

Text #12

Max Range: 3.7064. Min Range: -3.7064

Max Act: 3.5088. Min Act: -0.1700

Data Index: 5019715 (Open Web Text)

Max Activating Token Index: 210

Text #13

Max Range: 3.7064. Min Range: -3.7064

Max Act: 3.4796. Min Act: -0.1700

Data Index: 6482460 (Open Web Text)

Max Activating Token Index: 337

Text #14

Max Range: 3.7064. Min Range: -3.7064

Max Act: 3.4909. Min Act: -0.1700

Data Index: 5694553 (Open Web Text)

Max Activating Token Index: 83

Text #15

Max Range: 3.7064. Min Range: -3.7064

Max Act: 3.4706. Min Act: -0.1700

Data Index: 6836460 (Open Web Text)

Max Activating Token Index: 178

Text #16

Max Range: 3.7064. Min Range: -3.7064

Max Act: 3.4780. Min Act: -0.1700

Data Index: 1937991 (Open Web Text)

Max Activating Token Index: 358

Text #17

Max Range: 3.7064. Min Range: -3.7064

Max Act: 3.4743. Min Act: -0.1700

Data Index: 1069867 (Open Web Text)

Max Activating Token Index: 592

Text #18

Max Range: 3.7064. Min Range: -3.7064

Max Act: 3.4549. Min Act: -0.1700

Data Index: 5041297 (Open Web Text)

Max Activating Token Index: 906

Text #19

Max Range: 3.7064. Min Range: -3.7064

Max Act: 3.4600. Min Act: -0.1700

Data Index: 831133 (Open Web Text)

Max Activating Token Index: 634