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

Dataset: Open Web Text

Neuron 1451 in Layer 5

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: 3.5321. Min Range: -3.5321

Max Act: 3.5321. Min Act: -0.1700

Data Index: 4858268 (Open Web Text)

Max Activating Token Index: 186

Text #1

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.5163. Min Act: -0.1700

Data Index: 8154274 (Open Web Text)

Max Activating Token Index: 773

Text #2

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.4431. Min Act: -0.1700

Data Index: 6592699 (Open Web Text)

Max Activating Token Index: 241

Text #3

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.4430. Min Act: -0.1700

Data Index: 7204024 (Open Web Text)

Max Activating Token Index: 172

Text #4

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.3930. Min Act: -0.1700

Data Index: 567528 (Open Web Text)

Max Activating Token Index: 231

Text #5

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.3736. Min Act: -0.1700

Data Index: 6203025 (Open Web Text)

Max Activating Token Index: 183

Text #6

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.3438. Min Act: -0.1700

Data Index: 3599805 (Open Web Text)

Max Activating Token Index: 967

Text #7

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.3247. Min Act: -0.1700

Data Index: 1574002 (Open Web Text)

Max Activating Token Index: 882

Text #8

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.3112. Min Act: -0.1700

Data Index: 3342047 (Open Web Text)

Max Activating Token Index: 612

Text #9

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.3144. Min Act: -0.1700

Data Index: 5686576 (Open Web Text)

Max Activating Token Index: 585

Text #10

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.2964. Min Act: -0.1700

Data Index: 8220146 (Open Web Text)

Max Activating Token Index: 829

Text #11

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.2971. Min Act: -0.1700

Data Index: 5834528 (Open Web Text)

Max Activating Token Index: 706

Text #12

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.2814. Min Act: -0.1700

Data Index: 2165607 (Open Web Text)

Max Activating Token Index: 961

Text #13

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.2777. Min Act: -0.1700

Data Index: 793564 (Open Web Text)

Max Activating Token Index: 229

Text #14

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.2613. Min Act: -0.1700

Data Index: 6939745 (Open Web Text)

Max Activating Token Index: 812

Text #15

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.2693. Min Act: -0.1700

Data Index: 8420394 (Open Web Text)

Max Activating Token Index: 688

Text #16

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.2555. Min Act: -0.1700

Data Index: 4717743 (Open Web Text)

Max Activating Token Index: 84

Text #17

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.2461. Min Act: -0.1700

Data Index: 8188280 (Open Web Text)

Max Activating Token Index: 791

Text #18

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.2705. Min Act: -0.1700

Data Index: 8692120 (Open Web Text)

Max Activating Token Index: 188

Text #19

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.2603. Min Act: -0.1700

Data Index: 4737939 (Open Web Text)

Max Activating Token Index: 571