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

Dataset: Open Web Text

Neuron 183 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: 7.3474. Min Range: -7.3474

Max Act: 7.3074. Min Act: -0.1700

Data Index: 3337298 (Open Web Text)

Max Activating Token Index: 509

Text #1

Max Range: 7.3474. Min Range: -7.3474

Max Act: 7.3474. Min Act: -0.1700

Data Index: 3892331 (Open Web Text)

Max Activating Token Index: 457

Text #2

Max Range: 7.3474. Min Range: -7.3474

Max Act: 6.9756. Min Act: -0.1700

Data Index: 1064689 (Open Web Text)

Max Activating Token Index: 986

Text #3

Max Range: 7.3474. Min Range: -7.3474

Max Act: 6.9359. Min Act: -0.1700

Data Index: 2555359 (Open Web Text)

Max Activating Token Index: 607

Text #4

Max Range: 7.3474. Min Range: -7.3474

Max Act: 6.9596. Min Act: -0.1700

Data Index: 7931239 (Open Web Text)

Max Activating Token Index: 120

Text #5

Max Range: 7.3474. Min Range: -7.3474

Max Act: 6.9106. Min Act: -0.1700

Data Index: 3894095 (Open Web Text)

Max Activating Token Index: 646

Text #6

Max Range: 7.3474. Min Range: -7.3474

Max Act: 6.9740. Min Act: -0.1700

Data Index: 6263489 (Open Web Text)

Max Activating Token Index: 156

Text #7

Max Range: 7.3474. Min Range: -7.3474

Max Act: 6.9353. Min Act: -0.1700

Data Index: 2291780 (Open Web Text)

Max Activating Token Index: 407

Text #8

Max Range: 7.3474. Min Range: -7.3474

Max Act: 6.8824. Min Act: -0.1700

Data Index: 4959499 (Open Web Text)

Max Activating Token Index: 951

Text #9

Max Range: 7.3474. Min Range: -7.3474

Max Act: 6.8810. Min Act: -0.1700

Data Index: 6354657 (Open Web Text)

Max Activating Token Index: 463

Text #10

Max Range: 7.3474. Min Range: -7.3474

Max Act: 6.8070. Min Act: -0.1700

Data Index: 1786134 (Open Web Text)

Max Activating Token Index: 282

Text #11

Max Range: 7.3474. Min Range: -7.3474

Max Act: 6.7763. Min Act: -0.1700

Data Index: 8791691 (Open Web Text)

Max Activating Token Index: 520

Text #12

Max Range: 7.3474. Min Range: -7.3474

Max Act: 6.8145. Min Act: -0.1700

Data Index: 7458640 (Open Web Text)

Max Activating Token Index: 325

Text #13

Max Range: 7.3474. Min Range: -7.3474

Max Act: 6.8088. Min Act: -0.1700

Data Index: 101665 (Open Web Text)

Max Activating Token Index: 706

Text #14

Max Range: 7.3474. Min Range: -7.3474

Max Act: 6.8009. Min Act: -0.1700

Data Index: 3225424 (Open Web Text)

Max Activating Token Index: 770

Text #15

Max Range: 7.3474. Min Range: -7.3474

Max Act: 6.7776. Min Act: -0.1700

Data Index: 4673583 (Open Web Text)

Max Activating Token Index: 679

Text #16

Max Range: 7.3474. Min Range: -7.3474

Max Act: 6.7968. Min Act: -0.1700

Data Index: 4259132 (Open Web Text)

Max Activating Token Index: 386

Text #17

Max Range: 7.3474. Min Range: -7.3474

Max Act: 6.7569. Min Act: -0.1700

Data Index: 8662642 (Open Web Text)

Max Activating Token Index: 373

Text #18

Max Range: 7.3474. Min Range: -7.3474

Max Act: 6.7689. Min Act: -0.1700

Data Index: 6755734 (Open Web Text)

Max Activating Token Index: 755

Text #19

Max Range: 7.3474. Min Range: -7.3474

Max Act: 6.5999. Min Act: -0.1700

Data Index: 163365 (Open Web Text)

Max Activating Token Index: 1010