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

Dataset: Open Web Text

Neuron 575 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: 4.3947. Min Range: -4.3947

Max Act: 4.3947. Min Act: -0.1700

Data Index: 2406467 (Open Web Text)

Max Activating Token Index: 887

Text #1

Max Range: 4.3947. Min Range: -4.3947

Max Act: 4.3693. Min Act: -0.1700

Data Index: 7138141 (Open Web Text)

Max Activating Token Index: 145

Text #2

Max Range: 4.3947. Min Range: -4.3947

Max Act: 4.3387. Min Act: -0.1700

Data Index: 8664771 (Open Web Text)

Max Activating Token Index: 520

Text #3

Max Range: 4.3947. Min Range: -4.3947

Max Act: 4.3944. Min Act: -0.1700

Data Index: 7183188 (Open Web Text)

Max Activating Token Index: 884

Text #4

Max Range: 4.3947. Min Range: -4.3947

Max Act: 4.3319. Min Act: -0.1700

Data Index: 114913 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.3947. Min Range: -4.3947

Max Act: 4.2956. Min Act: -0.1700

Data Index: 3883030 (Open Web Text)

Max Activating Token Index: 205

Text #6

Max Range: 4.3947. Min Range: -4.3947

Max Act: 4.2860. Min Act: -0.1700

Data Index: 2795431 (Open Web Text)

Max Activating Token Index: 651

Text #7

Max Range: 4.3947. Min Range: -4.3947

Max Act: 4.2355. Min Act: -0.1700

Data Index: 7189181 (Open Web Text)

Max Activating Token Index: 394

Text #8

Max Range: 4.3947. Min Range: -4.3947

Max Act: 4.2330. Min Act: -0.1700

Data Index: 3936832 (Open Web Text)

Max Activating Token Index: 101

Text #9

Max Range: 4.3947. Min Range: -4.3947

Max Act: 4.2407. Min Act: -0.1700

Data Index: 4877197 (Open Web Text)

Max Activating Token Index: 20

Text #10

Max Range: 4.3947. Min Range: -4.3947

Max Act: 4.2366. Min Act: -0.1700

Data Index: 782937 (Open Web Text)

Max Activating Token Index: 16

Text #11

Max Range: 4.3947. Min Range: -4.3947

Max Act: 4.2519. Min Act: -0.1700

Data Index: 5260924 (Open Web Text)

Max Activating Token Index: 849

Text #12

Max Range: 4.3947. Min Range: -4.3947

Max Act: 4.2043. Min Act: -0.1700

Data Index: 2493777 (Open Web Text)

Max Activating Token Index: 292

Text #13

Max Range: 4.3947. Min Range: -4.3947

Max Act: 4.2202. Min Act: -0.1700

Data Index: 3611192 (Open Web Text)

Max Activating Token Index: 418

Text #14

Max Range: 4.3947. Min Range: -4.3947

Max Act: 4.1632. Min Act: -0.1700

Data Index: 8700058 (Open Web Text)

Max Activating Token Index: 445

Text #15

Max Range: 4.3947. Min Range: -4.3947

Max Act: 4.2346. Min Act: -0.1700

Data Index: 668303 (Open Web Text)

Max Activating Token Index: 834

Text #16

Max Range: 4.3947. Min Range: -4.3947

Max Act: 4.2033. Min Act: -0.1700

Data Index: 2253321 (Open Web Text)

Max Activating Token Index: 359

Text #17

Max Range: 4.3947. Min Range: -4.3947

Max Act: 4.2424. Min Act: -0.1700

Data Index: 3494411 (Open Web Text)

Max Activating Token Index: 423

Text #18

Max Range: 4.3947. Min Range: -4.3947

Max Act: 4.2230. Min Act: -0.1700

Data Index: 5044101 (Open Web Text)

Max Activating Token Index: 709

Text #19

Max Range: 4.3947. Min Range: -4.3947

Max Act: 4.1829. Min Act: -0.1700

Data Index: 3227843 (Open Web Text)

Max Activating Token Index: 902