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

Dataset: Open Web Text

Neuron 1527 in Layer 4

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: 4.0714. Min Range: -4.0714

Max Act: 4.0714. Min Act: -0.1700

Data Index: 2771040 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 4.0714. Min Range: -4.0714

Max Act: 4.0714. Min Act: -0.1700

Data Index: 820382 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 4.0714. Min Range: -4.0714

Max Act: 3.9973. Min Act: -0.1700

Data Index: 7646730 (Open Web Text)

Max Activating Token Index: 956

Text #3

Max Range: 4.0714. Min Range: -4.0714

Max Act: 4.0099. Min Act: -0.1700

Data Index: 7662623 (Open Web Text)

Max Activating Token Index: 199

Text #4

Max Range: 4.0714. Min Range: -4.0714

Max Act: 3.9508. Min Act: -0.1700

Data Index: 3225361 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.0714. Min Range: -4.0714

Max Act: 3.9099. Min Act: -0.1700

Data Index: 1856054 (Open Web Text)

Max Activating Token Index: 366

Text #6

Max Range: 4.0714. Min Range: -4.0714

Max Act: 3.9463. Min Act: -0.1700

Data Index: 3497727 (Open Web Text)

Max Activating Token Index: 597

Text #7

Max Range: 4.0714. Min Range: -4.0714

Max Act: 3.9026. Min Act: -0.1700

Data Index: 4514052 (Open Web Text)

Max Activating Token Index: 762

Text #8

Max Range: 4.0714. Min Range: -4.0714

Max Act: 3.9042. Min Act: -0.1700

Data Index: 2314907 (Open Web Text)

Max Activating Token Index: 807

Text #9

Max Range: 4.0714. Min Range: -4.0714

Max Act: 3.9423. Min Act: -0.1700

Data Index: 1868650 (Open Web Text)

Max Activating Token Index: 242

Text #10

Max Range: 4.0714. Min Range: -4.0714

Max Act: 3.9381. Min Act: -0.1700

Data Index: 5476051 (Open Web Text)

Max Activating Token Index: 887

Text #11

Max Range: 4.0714. Min Range: -4.0714

Max Act: 3.8913. Min Act: -0.1700

Data Index: 937010 (Open Web Text)

Max Activating Token Index: 145

Text #12

Max Range: 4.0714. Min Range: -4.0714

Max Act: 3.9177. Min Act: -0.1700

Data Index: 5822415 (Open Web Text)

Max Activating Token Index: 1015

Text #13

Max Range: 4.0714. Min Range: -4.0714

Max Act: 3.8824. Min Act: -0.1700

Data Index: 647273 (Open Web Text)

Max Activating Token Index: 528

Text #14

Max Range: 4.0714. Min Range: -4.0714

Max Act: 3.8969. Min Act: -0.1700

Data Index: 3271162 (Open Web Text)

Max Activating Token Index: 171

Text #15

Max Range: 4.0714. Min Range: -4.0714

Max Act: 3.9100. Min Act: -0.1700

Data Index: 509905 (Open Web Text)

Max Activating Token Index: 136

Text #16

Max Range: 4.0714. Min Range: -4.0714

Max Act: 3.8711. Min Act: -0.1700

Data Index: 4432 (Open Web Text)

Max Activating Token Index: 87

Text #17

Max Range: 4.0714. Min Range: -4.0714

Max Act: 3.8705. Min Act: -0.1700

Data Index: 6458838 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 4.0714. Min Range: -4.0714

Max Act: 3.8832. Min Act: -0.1700

Data Index: 5822416 (Open Web Text)

Max Activating Token Index: 591

Text #19

Max Range: 4.0714. Min Range: -4.0714

Max Act: 3.8691. Min Act: -0.1700

Data Index: 5545567 (Open Web Text)

Max Activating Token Index: 455