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

Dataset: Open Web Text

Neuron 159 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: 4.3819. Min Range: -4.3819

Max Act: 4.3819. Min Act: -0.1700

Data Index: 506428 (Open Web Text)

Max Activating Token Index: 399

Text #1

Max Range: 4.3819. Min Range: -4.3819

Max Act: 4.3180. Min Act: -0.1700

Data Index: 8188558 (Open Web Text)

Max Activating Token Index: 310

Text #2

Max Range: 4.3819. Min Range: -4.3819

Max Act: 4.3355. Min Act: -0.1700

Data Index: 6051405 (Open Web Text)

Max Activating Token Index: 899

Text #3

Max Range: 4.3819. Min Range: -4.3819

Max Act: 4.3091. Min Act: -0.1700

Data Index: 5188633 (Open Web Text)

Max Activating Token Index: 593

Text #4

Max Range: 4.3819. Min Range: -4.3819

Max Act: 4.2849. Min Act: -0.1700

Data Index: 6372625 (Open Web Text)

Max Activating Token Index: 531

Text #5

Max Range: 4.3819. Min Range: -4.3819

Max Act: 4.2942. Min Act: -0.1700

Data Index: 2923020 (Open Web Text)

Max Activating Token Index: 362

Text #6

Max Range: 4.3819. Min Range: -4.3819

Max Act: 4.3236. Min Act: -0.1700

Data Index: 3740904 (Open Web Text)

Max Activating Token Index: 974

Text #7

Max Range: 4.3819. Min Range: -4.3819

Max Act: 4.2521. Min Act: -0.1700

Data Index: 1799857 (Open Web Text)

Max Activating Token Index: 317

Text #8

Max Range: 4.3819. Min Range: -4.3819

Max Act: 4.2871. Min Act: -0.1700

Data Index: 8533577 (Open Web Text)

Max Activating Token Index: 256

Text #9

Max Range: 4.3819. Min Range: -4.3819

Max Act: 4.2473. Min Act: -0.1700

Data Index: 3420531 (Open Web Text)

Max Activating Token Index: 558

Text #10

Max Range: 4.3819. Min Range: -4.3819

Max Act: 4.2716. Min Act: -0.1700

Data Index: 3426742 (Open Web Text)

Max Activating Token Index: 628

Text #11

Max Range: 4.3819. Min Range: -4.3819

Max Act: 4.2142. Min Act: -0.1700

Data Index: 8580918 (Open Web Text)

Max Activating Token Index: 537

Text #12

Max Range: 4.3819. Min Range: -4.3819

Max Act: 4.2495. Min Act: -0.1700

Data Index: 2032310 (Open Web Text)

Max Activating Token Index: 550

Text #13

Max Range: 4.3819. Min Range: -4.3819

Max Act: 4.2402. Min Act: -0.1700

Data Index: 195425 (Open Web Text)

Max Activating Token Index: 686

Text #14

Max Range: 4.3819. Min Range: -4.3819

Max Act: 4.2339. Min Act: -0.1700

Data Index: 5723505 (Open Web Text)

Max Activating Token Index: 591

Text #15

Max Range: 4.3819. Min Range: -4.3819

Max Act: 4.2485. Min Act: -0.1700

Data Index: 1375160 (Open Web Text)

Max Activating Token Index: 220

Text #16

Max Range: 4.3819. Min Range: -4.3819

Max Act: 4.2574. Min Act: -0.1700

Data Index: 719602 (Open Web Text)

Max Activating Token Index: 652

Text #17

Max Range: 4.3819. Min Range: -4.3819

Max Act: 4.2191. Min Act: -0.1700

Data Index: 3073301 (Open Web Text)

Max Activating Token Index: 921

Text #18

Max Range: 4.3819. Min Range: -4.3819

Max Act: 4.2503. Min Act: -0.1700

Data Index: 4957120 (Open Web Text)

Max Activating Token Index: 461

Text #19

Max Range: 4.3819. Min Range: -4.3819

Max Act: 4.2124. Min Act: -0.1700

Data Index: 5011826 (Open Web Text)

Max Activating Token Index: 414