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

Dataset: Open Web Text

Neuron 2491 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: 2.9183. Min Range: -2.9183

Max Act: 2.9183. Min Act: -0.1700

Data Index: 3173730 (Open Web Text)

Max Activating Token Index: 890

Text #1

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.8913. Min Act: -0.1700

Data Index: 6415339 (Open Web Text)

Max Activating Token Index: 333

Text #2

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.9030. Min Act: -0.1700

Data Index: 7562617 (Open Web Text)

Max Activating Token Index: 741

Text #3

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.8802. Min Act: -0.1700

Data Index: 8798703 (Open Web Text)

Max Activating Token Index: 548

Text #4

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.8806. Min Act: -0.1700

Data Index: 6734663 (Open Web Text)

Max Activating Token Index: 141

Text #5

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.8382. Min Act: -0.1700

Data Index: 5251481 (Open Web Text)

Max Activating Token Index: 292

Text #6

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.8562. Min Act: -0.1700

Data Index: 7018116 (Open Web Text)

Max Activating Token Index: 660

Text #7

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.8719. Min Act: -0.1700

Data Index: 4832673 (Open Web Text)

Max Activating Token Index: 404

Text #8

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.8314. Min Act: -0.1700

Data Index: 6268154 (Open Web Text)

Max Activating Token Index: 807

Text #9

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.8349. Min Act: -0.1700

Data Index: 3415872 (Open Web Text)

Max Activating Token Index: 677

Text #10

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.7820. Min Act: -0.1700

Data Index: 6783371 (Open Web Text)

Max Activating Token Index: 660

Text #11

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.8022. Min Act: -0.1700

Data Index: 2772763 (Open Web Text)

Max Activating Token Index: 493

Text #12

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.7726. Min Act: -0.1700

Data Index: 3154175 (Open Web Text)

Max Activating Token Index: 299

Text #13

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.7798. Min Act: -0.1700

Data Index: 8000886 (Open Web Text)

Max Activating Token Index: 899

Text #14

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.7806. Min Act: -0.1700

Data Index: 1540429 (Open Web Text)

Max Activating Token Index: 419

Text #15

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.7915. Min Act: -0.1700

Data Index: 4722782 (Open Web Text)

Max Activating Token Index: 37

Text #16

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.7954. Min Act: -0.1700

Data Index: 5200521 (Open Web Text)

Max Activating Token Index: 657

Text #17

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.7550. Min Act: -0.1700

Data Index: 5761628 (Open Web Text)

Max Activating Token Index: 180

Text #18

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.7680. Min Act: -0.1700

Data Index: 6115307 (Open Web Text)

Max Activating Token Index: 377

Text #19

Max Range: 2.9183. Min Range: -2.9183

Max Act: 2.7628. Min Act: -0.1700

Data Index: 1754610 (Open Web Text)

Max Activating Token Index: 909