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

Dataset: Open Web Text

Neuron 75 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: 3.7144. Min Range: -3.7144

Max Act: 3.7012. Min Act: -0.1700

Data Index: 1452704 (Open Web Text)

Max Activating Token Index: 386

Text #1

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.7046. Min Act: -0.1700

Data Index: 7935522 (Open Web Text)

Max Activating Token Index: 433

Text #2

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.7144. Min Act: -0.1700

Data Index: 4557422 (Open Web Text)

Max Activating Token Index: 803

Text #3

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.6259. Min Act: -0.1700

Data Index: 1823220 (Open Web Text)

Max Activating Token Index: 880

Text #4

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.6958. Min Act: -0.1700

Data Index: 5072315 (Open Web Text)

Max Activating Token Index: 548

Text #5

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.6157. Min Act: -0.1700

Data Index: 4376799 (Open Web Text)

Max Activating Token Index: 886

Text #6

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.6613. Min Act: -0.1700

Data Index: 3060327 (Open Web Text)

Max Activating Token Index: 273

Text #7

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.6036. Min Act: -0.1700

Data Index: 367162 (Open Web Text)

Max Activating Token Index: 526

Text #8

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.6220. Min Act: -0.1700

Data Index: 5568893 (Open Web Text)

Max Activating Token Index: 847

Text #9

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.6010. Min Act: -0.1700

Data Index: 8628541 (Open Web Text)

Max Activating Token Index: 549

Text #10

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.5910. Min Act: -0.1700

Data Index: 8389571 (Open Web Text)

Max Activating Token Index: 600

Text #11

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.5941. Min Act: -0.1700

Data Index: 2511959 (Open Web Text)

Max Activating Token Index: 661

Text #12

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.5606. Min Act: -0.1700

Data Index: 2600004 (Open Web Text)

Max Activating Token Index: 468

Text #13

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.5274. Min Act: -0.1700

Data Index: 3388517 (Open Web Text)

Max Activating Token Index: 774

Text #14

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.5463. Min Act: -0.1700

Data Index: 7409234 (Open Web Text)

Max Activating Token Index: 697

Text #15

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.5688. Min Act: -0.1700

Data Index: 8238434 (Open Web Text)

Max Activating Token Index: 40

Text #16

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.5550. Min Act: -0.1700

Data Index: 7977760 (Open Web Text)

Max Activating Token Index: 58

Text #17

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.5410. Min Act: -0.1700

Data Index: 2726151 (Open Web Text)

Max Activating Token Index: 793

Text #18

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.5019. Min Act: -0.1700

Data Index: 741237 (Open Web Text)

Max Activating Token Index: 385

Text #19

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.5108. Min Act: -0.1700

Data Index: 7445243 (Open Web Text)

Max Activating Token Index: 549