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

Dataset: Open Web Text

Neuron 2321 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: 4.5948. Min Range: -4.5948

Max Act: 4.5925. Min Act: -0.1700

Data Index: 3561516 (Open Web Text)

Max Activating Token Index: 631

Text #1

Max Range: 4.5948. Min Range: -4.5948

Max Act: 4.5948. Min Act: -0.1700

Data Index: 540346 (Open Web Text)

Max Activating Token Index: 422

Text #2

Max Range: 4.5948. Min Range: -4.5948

Max Act: 4.4883. Min Act: -0.1700

Data Index: 5454354 (Open Web Text)

Max Activating Token Index: 242

Text #3

Max Range: 4.5948. Min Range: -4.5948

Max Act: 4.4507. Min Act: -0.1700

Data Index: 596676 (Open Web Text)

Max Activating Token Index: 1019

Text #4

Max Range: 4.5948. Min Range: -4.5948

Max Act: 4.4795. Min Act: -0.1700

Data Index: 7667472 (Open Web Text)

Max Activating Token Index: 711

Text #5

Max Range: 4.5948. Min Range: -4.5948

Max Act: 4.4907. Min Act: -0.1700

Data Index: 8317758 (Open Web Text)

Max Activating Token Index: 105

Text #6

Max Range: 4.5948. Min Range: -4.5948

Max Act: 4.4655. Min Act: -0.1700

Data Index: 494961 (Open Web Text)

Max Activating Token Index: 264

Text #7

Max Range: 4.5948. Min Range: -4.5948

Max Act: 4.4341. Min Act: -0.1700

Data Index: 2843117 (Open Web Text)

Max Activating Token Index: 779

Text #8

Max Range: 4.5948. Min Range: -4.5948

Max Act: 4.3988. Min Act: -0.1700

Data Index: 6196347 (Open Web Text)

Max Activating Token Index: 240

Text #9

Max Range: 4.5948. Min Range: -4.5948

Max Act: 4.3226. Min Act: -0.1700

Data Index: 221005 (Open Web Text)

Max Activating Token Index: 408

Text #10

Max Range: 4.5948. Min Range: -4.5948

Max Act: 4.3633. Min Act: -0.1700

Data Index: 6524489 (Open Web Text)

Max Activating Token Index: 941

Text #11

Max Range: 4.5948. Min Range: -4.5948

Max Act: 4.3726. Min Act: -0.1700

Data Index: 388039 (Open Web Text)

Max Activating Token Index: 962

Text #12

Max Range: 4.5948. Min Range: -4.5948

Max Act: 4.2845. Min Act: -0.1700

Data Index: 3180409 (Open Web Text)

Max Activating Token Index: 477

Text #13

Max Range: 4.5948. Min Range: -4.5948

Max Act: 4.3027. Min Act: -0.1700

Data Index: 2811482 (Open Web Text)

Max Activating Token Index: 292

Text #14

Max Range: 4.5948. Min Range: -4.5948

Max Act: 4.2674. Min Act: -0.1700

Data Index: 2519077 (Open Web Text)

Max Activating Token Index: 324

Text #15

Max Range: 4.5948. Min Range: -4.5948

Max Act: 4.2766. Min Act: -0.1700

Data Index: 8473176 (Open Web Text)

Max Activating Token Index: 187

Text #16

Max Range: 4.5948. Min Range: -4.5948

Max Act: 4.2503. Min Act: -0.1700

Data Index: 1028285 (Open Web Text)

Max Activating Token Index: 298

Text #17

Max Range: 4.5948. Min Range: -4.5948

Max Act: 4.3166. Min Act: -0.1700

Data Index: 6931275 (Open Web Text)

Max Activating Token Index: 981

Text #18

Max Range: 4.5948. Min Range: -4.5948

Max Act: 4.2485. Min Act: -0.1700

Data Index: 7164673 (Open Web Text)

Max Activating Token Index: 288

Text #19

Max Range: 4.5948. Min Range: -4.5948

Max Act: 4.2673. Min Act: -0.1700

Data Index: 5490506 (Open Web Text)

Max Activating Token Index: 687