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

Dataset: Open Web Text

Neuron 2337 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: 4.2567. Min Range: -4.2567

Max Act: 4.2567. Min Act: -0.1700

Data Index: 4682660 (Open Web Text)

Max Activating Token Index: 230

Text #1

Max Range: 4.2567. Min Range: -4.2567

Max Act: 4.0343. Min Act: -0.1700

Data Index: 3073513 (Open Web Text)

Max Activating Token Index: 463

Text #2

Max Range: 4.2567. Min Range: -4.2567

Max Act: 3.9616. Min Act: -0.1700

Data Index: 1457523 (Open Web Text)

Max Activating Token Index: 61

Text #3

Max Range: 4.2567. Min Range: -4.2567

Max Act: 3.9729. Min Act: -0.1700

Data Index: 6535450 (Open Web Text)

Max Activating Token Index: 61

Text #4

Max Range: 4.2567. Min Range: -4.2567

Max Act: 3.9862. Min Act: -0.1700

Data Index: 8244382 (Open Web Text)

Max Activating Token Index: 892

Text #5

Max Range: 4.2567. Min Range: -4.2567

Max Act: 3.9698. Min Act: -0.1700

Data Index: 3350690 (Open Web Text)

Max Activating Token Index: 600

Text #6

Max Range: 4.2567. Min Range: -4.2567

Max Act: 3.9476. Min Act: -0.1700

Data Index: 4310853 (Open Web Text)

Max Activating Token Index: 523

Text #7

Max Range: 4.2567. Min Range: -4.2567

Max Act: 3.9108. Min Act: -0.1700

Data Index: 501836 (Open Web Text)

Max Activating Token Index: 494

Text #8

Max Range: 4.2567. Min Range: -4.2567

Max Act: 3.9003. Min Act: -0.1700

Data Index: 6547483 (Open Web Text)

Max Activating Token Index: 685

Text #9

Max Range: 4.2567. Min Range: -4.2567

Max Act: 3.9503. Min Act: -0.1700

Data Index: 6741575 (Open Web Text)

Max Activating Token Index: 812

Text #10

Max Range: 4.2567. Min Range: -4.2567

Max Act: 3.8704. Min Act: -0.1700

Data Index: 1540672 (Open Web Text)

Max Activating Token Index: 902

Text #11

Max Range: 4.2567. Min Range: -4.2567

Max Act: 3.8980. Min Act: -0.1700

Data Index: 6427496 (Open Web Text)

Max Activating Token Index: 968

Text #12

Max Range: 4.2567. Min Range: -4.2567

Max Act: 3.8965. Min Act: -0.1700

Data Index: 8555159 (Open Web Text)

Max Activating Token Index: 347

Text #13

Max Range: 4.2567. Min Range: -4.2567

Max Act: 3.8890. Min Act: -0.1700

Data Index: 385235 (Open Web Text)

Max Activating Token Index: 1004

Text #14

Max Range: 4.2567. Min Range: -4.2567

Max Act: 3.8442. Min Act: -0.1700

Data Index: 6872161 (Open Web Text)

Max Activating Token Index: 887

Text #15

Max Range: 4.2567. Min Range: -4.2567

Max Act: 3.8467. Min Act: -0.1700

Data Index: 5437541 (Open Web Text)

Max Activating Token Index: 506

Text #16

Max Range: 4.2567. Min Range: -4.2567

Max Act: 3.8544. Min Act: -0.1700

Data Index: 5149367 (Open Web Text)

Max Activating Token Index: 685

Text #17

Max Range: 4.2567. Min Range: -4.2567

Max Act: 3.8575. Min Act: -0.1700

Data Index: 1416700 (Open Web Text)

Max Activating Token Index: 349

Text #18

Max Range: 4.2567. Min Range: -4.2567

Max Act: 3.7857. Min Act: -0.1700

Data Index: 6285470 (Open Web Text)

Max Activating Token Index: 437

Text #19

Max Range: 4.2567. Min Range: -4.2567

Max Act: 3.7962. Min Act: -0.1700

Data Index: 706577 (Open Web Text)

Max Activating Token Index: 721