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

Dataset: Open Web Text

Neuron 1577 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: 3.4488. Min Range: -3.4488

Max Act: 3.4488. Min Act: -0.1700

Data Index: 473487 (Open Web Text)

Max Activating Token Index: 1017

Text #1

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.4334. Min Act: -0.1700

Data Index: 3906127 (Open Web Text)

Max Activating Token Index: 710

Text #2

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.4113. Min Act: -0.1700

Data Index: 3383937 (Open Web Text)

Max Activating Token Index: 204

Text #3

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.3921. Min Act: -0.1700

Data Index: 2891958 (Open Web Text)

Max Activating Token Index: 484

Text #4

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.4174. Min Act: -0.1700

Data Index: 155312 (Open Web Text)

Max Activating Token Index: 632

Text #5

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.3677. Min Act: -0.1700

Data Index: 3302191 (Open Web Text)

Max Activating Token Index: 947

Text #6

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.3979. Min Act: -0.1700

Data Index: 5441621 (Open Web Text)

Max Activating Token Index: 167

Text #7

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.3927. Min Act: -0.1700

Data Index: 6804587 (Open Web Text)

Max Activating Token Index: 496

Text #8

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.3742. Min Act: -0.1700

Data Index: 8170416 (Open Web Text)

Max Activating Token Index: 904

Text #9

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.4062. Min Act: -0.1700

Data Index: 434078 (Open Web Text)

Max Activating Token Index: 503

Text #10

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.3883. Min Act: -0.1700

Data Index: 4620975 (Open Web Text)

Max Activating Token Index: 43

Text #11

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.3462. Min Act: -0.1700

Data Index: 326181 (Open Web Text)

Max Activating Token Index: 734

Text #12

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.3664. Min Act: -0.1700

Data Index: 6557927 (Open Web Text)

Max Activating Token Index: 534

Text #13

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.3560. Min Act: -0.1700

Data Index: 7371028 (Open Web Text)

Max Activating Token Index: 795

Text #14

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.3558. Min Act: -0.1700

Data Index: 88159 (Open Web Text)

Max Activating Token Index: 610

Text #15

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.3198. Min Act: -0.1700

Data Index: 3484466 (Open Web Text)

Max Activating Token Index: 387

Text #16

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.3451. Min Act: -0.1700

Data Index: 3716054 (Open Web Text)

Max Activating Token Index: 686

Text #17

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.3486. Min Act: -0.1700

Data Index: 4471942 (Open Web Text)

Max Activating Token Index: 842

Text #18

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.3316. Min Act: -0.1700

Data Index: 6792693 (Open Web Text)

Max Activating Token Index: 673

Text #19

Max Range: 3.4488. Min Range: -3.4488

Max Act: 3.3584. Min Act: -0.1700

Data Index: 6283074 (Open Web Text)

Max Activating Token Index: 829