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

Dataset: Open Web Text

Neuron 1122 in Layer 2

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: 6.0307. Min Range: -6.0307

Max Act: 6.0307. Min Act: -0.1700

Data Index: 6456999 (Open Web Text)

Max Activating Token Index: 492

Text #1

Max Range: 6.0307. Min Range: -6.0307

Max Act: 5.7826. Min Act: -0.1700

Data Index: 5222421 (Open Web Text)

Max Activating Token Index: 380

Text #2

Max Range: 6.0307. Min Range: -6.0307

Max Act: 5.8322. Min Act: -0.1700

Data Index: 8375247 (Open Web Text)

Max Activating Token Index: 489

Text #3

Max Range: 6.0307. Min Range: -6.0307

Max Act: 5.7824. Min Act: -0.1700

Data Index: 6594174 (Open Web Text)

Max Activating Token Index: 332

Text #4

Max Range: 6.0307. Min Range: -6.0307

Max Act: 5.8145. Min Act: -0.1700

Data Index: 4345811 (Open Web Text)

Max Activating Token Index: 145

Text #5

Max Range: 6.0307. Min Range: -6.0307

Max Act: 5.8063. Min Act: -0.1700

Data Index: 1006254 (Open Web Text)

Max Activating Token Index: 571

Text #6

Max Range: 6.0307. Min Range: -6.0307

Max Act: 5.7395. Min Act: -0.1700

Data Index: 3814395 (Open Web Text)

Max Activating Token Index: 749

Text #7

Max Range: 6.0307. Min Range: -6.0307

Max Act: 5.7030. Min Act: -0.1700

Data Index: 55117 (Open Web Text)

Max Activating Token Index: 552

Text #8

Max Range: 6.0307. Min Range: -6.0307

Max Act: 5.8020. Min Act: -0.1700

Data Index: 7852104 (Open Web Text)

Max Activating Token Index: 550

Text #9

Max Range: 6.0307. Min Range: -6.0307

Max Act: 5.7848. Min Act: -0.1700

Data Index: 988913 (Open Web Text)

Max Activating Token Index: 641

Text #10

Max Range: 6.0307. Min Range: -6.0307

Max Act: 5.7624. Min Act: -0.1700

Data Index: 7824732 (Open Web Text)

Max Activating Token Index: 611

Text #11

Max Range: 6.0307. Min Range: -6.0307

Max Act: 5.7545. Min Act: -0.1700

Data Index: 651065 (Open Web Text)

Max Activating Token Index: 597

Text #12

Max Range: 6.0307. Min Range: -6.0307

Max Act: 5.7376. Min Act: -0.1700

Data Index: 37976 (Open Web Text)

Max Activating Token Index: 306

Text #13

Max Range: 6.0307. Min Range: -6.0307

Max Act: 5.7199. Min Act: -0.1700

Data Index: 8146390 (Open Web Text)

Max Activating Token Index: 550

Text #14

Max Range: 6.0307. Min Range: -6.0307

Max Act: 5.7530. Min Act: -0.1700

Data Index: 7913920 (Open Web Text)

Max Activating Token Index: 591

Text #15

Max Range: 6.0307. Min Range: -6.0307

Max Act: 5.7259. Min Act: -0.1700

Data Index: 6455301 (Open Web Text)

Max Activating Token Index: 410

Text #16

Max Range: 6.0307. Min Range: -6.0307

Max Act: 5.7051. Min Act: -0.1700

Data Index: 5769078 (Open Web Text)

Max Activating Token Index: 475

Text #17

Max Range: 6.0307. Min Range: -6.0307

Max Act: 5.7550. Min Act: -0.1700

Data Index: 5565288 (Open Web Text)

Max Activating Token Index: 462

Text #18

Max Range: 6.0307. Min Range: -6.0307

Max Act: 5.7175. Min Act: -0.1700

Data Index: 4403082 (Open Web Text)

Max Activating Token Index: 259

Text #19

Max Range: 6.0307. Min Range: -6.0307

Max Act: 5.7213. Min Act: -0.1700

Data Index: 1773074 (Open Web Text)

Max Activating Token Index: 648