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

Dataset: Open Web Text

Neuron 972 in Layer 3

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: 4.7347. Min Range: -4.7347

Max Act: 4.7347. Min Act: -0.1700

Data Index: 2757435 (Open Web Text)

Max Activating Token Index: 453

Text #1

Max Range: 4.7347. Min Range: -4.7347

Max Act: 4.6139. Min Act: -0.1700

Data Index: 4370981 (Open Web Text)

Max Activating Token Index: 44

Text #2

Max Range: 4.7347. Min Range: -4.7347

Max Act: 4.6125. Min Act: -0.1700

Data Index: 7820746 (Open Web Text)

Max Activating Token Index: 319

Text #3

Max Range: 4.7347. Min Range: -4.7347

Max Act: 4.5775. Min Act: -0.1700

Data Index: 5401838 (Open Web Text)

Max Activating Token Index: 489

Text #4

Max Range: 4.7347. Min Range: -4.7347

Max Act: 4.6266. Min Act: -0.1700

Data Index: 7447303 (Open Web Text)

Max Activating Token Index: 239

Text #5

Max Range: 4.7347. Min Range: -4.7347

Max Act: 4.5533. Min Act: -0.1700

Data Index: 628338 (Open Web Text)

Max Activating Token Index: 335

Text #6

Max Range: 4.7347. Min Range: -4.7347

Max Act: 4.5514. Min Act: -0.1700

Data Index: 446806 (Open Web Text)

Max Activating Token Index: 179

Text #7

Max Range: 4.7347. Min Range: -4.7347

Max Act: 4.5280. Min Act: -0.1700

Data Index: 6658742 (Open Web Text)

Max Activating Token Index: 250

Text #8

Max Range: 4.7347. Min Range: -4.7347

Max Act: 4.5103. Min Act: -0.1700

Data Index: 3962386 (Open Web Text)

Max Activating Token Index: 737

Text #9

Max Range: 4.7347. Min Range: -4.7347

Max Act: 4.4515. Min Act: -0.1700

Data Index: 6821841 (Open Web Text)

Max Activating Token Index: 94

Text #10

Max Range: 4.7347. Min Range: -4.7347

Max Act: 4.4715. Min Act: -0.1700

Data Index: 7787818 (Open Web Text)

Max Activating Token Index: 642

Text #11

Max Range: 4.7347. Min Range: -4.7347

Max Act: 4.4517. Min Act: -0.1700

Data Index: 229667 (Open Web Text)

Max Activating Token Index: 946

Text #12

Max Range: 4.7347. Min Range: -4.7347

Max Act: 4.4771. Min Act: -0.1700

Data Index: 408920 (Open Web Text)

Max Activating Token Index: 324

Text #13

Max Range: 4.7347. Min Range: -4.7347

Max Act: 4.4277. Min Act: -0.1700

Data Index: 3581155 (Open Web Text)

Max Activating Token Index: 479

Text #14

Max Range: 4.7347. Min Range: -4.7347

Max Act: 4.4200. Min Act: -0.1700

Data Index: 3866433 (Open Web Text)

Max Activating Token Index: 820

Text #15

Max Range: 4.7347. Min Range: -4.7347

Max Act: 4.4509. Min Act: -0.1700

Data Index: 4440001 (Open Web Text)

Max Activating Token Index: 755

Text #16

Max Range: 4.7347. Min Range: -4.7347

Max Act: 4.4416. Min Act: -0.1700

Data Index: 6241585 (Open Web Text)

Max Activating Token Index: 708

Text #17

Max Range: 4.7347. Min Range: -4.7347

Max Act: 4.4443. Min Act: -0.1700

Data Index: 6360495 (Open Web Text)

Max Activating Token Index: 612

Text #18

Max Range: 4.7347. Min Range: -4.7347

Max Act: 4.4417. Min Act: -0.1700

Data Index: 6413601 (Open Web Text)

Max Activating Token Index: 585

Text #19

Max Range: 4.7347. Min Range: -4.7347

Max Act: 4.4265. Min Act: -0.1700

Data Index: 971127 (Open Web Text)

Max Activating Token Index: 318