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

Dataset: Open Web Text

Neuron 2205 in Layer 6

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: 4.6076. Min Range: -4.6076

Max Act: 4.5905. Min Act: -0.1700

Data Index: 8229231 (Open Web Text)

Max Activating Token Index: 589

Text #1

Max Range: 4.6076. Min Range: -4.6076

Max Act: 4.6076. Min Act: -0.1700

Data Index: 5286989 (Open Web Text)

Max Activating Token Index: 876

Text #2

Max Range: 4.6076. Min Range: -4.6076

Max Act: 4.5602. Min Act: -0.1700

Data Index: 328154 (Open Web Text)

Max Activating Token Index: 523

Text #3

Max Range: 4.6076. Min Range: -4.6076

Max Act: 4.5187. Min Act: -0.1700

Data Index: 5169299 (Open Web Text)

Max Activating Token Index: 22

Text #4

Max Range: 4.6076. Min Range: -4.6076

Max Act: 4.5182. Min Act: -0.1700

Data Index: 45537 (Open Web Text)

Max Activating Token Index: 229

Text #5

Max Range: 4.6076. Min Range: -4.6076

Max Act: 4.5167. Min Act: -0.1700

Data Index: 2001716 (Open Web Text)

Max Activating Token Index: 111

Text #6

Max Range: 4.6076. Min Range: -4.6076

Max Act: 4.4969. Min Act: -0.1700

Data Index: 7302758 (Open Web Text)

Max Activating Token Index: 381

Text #7

Max Range: 4.6076. Min Range: -4.6076

Max Act: 4.5229. Min Act: -0.1700

Data Index: 513766 (Open Web Text)

Max Activating Token Index: 297

Text #8

Max Range: 4.6076. Min Range: -4.6076

Max Act: 4.5147. Min Act: -0.1700

Data Index: 6436754 (Open Web Text)

Max Activating Token Index: 368

Text #9

Max Range: 4.6076. Min Range: -4.6076

Max Act: 4.5338. Min Act: -0.1700

Data Index: 7333421 (Open Web Text)

Max Activating Token Index: 418

Text #10

Max Range: 4.6076. Min Range: -4.6076

Max Act: 4.4771. Min Act: -0.1700

Data Index: 1422144 (Open Web Text)

Max Activating Token Index: 518

Text #11

Max Range: 4.6076. Min Range: -4.6076

Max Act: 4.4887. Min Act: -0.1700

Data Index: 295174 (Open Web Text)

Max Activating Token Index: 722

Text #12

Max Range: 4.6076. Min Range: -4.6076

Max Act: 4.4742. Min Act: -0.1700

Data Index: 7199031 (Open Web Text)

Max Activating Token Index: 524

Text #13

Max Range: 4.6076. Min Range: -4.6076

Max Act: 4.4655. Min Act: -0.1700

Data Index: 5525108 (Open Web Text)

Max Activating Token Index: 919

Text #14

Max Range: 4.6076. Min Range: -4.6076

Max Act: 4.4479. Min Act: -0.1700

Data Index: 4317236 (Open Web Text)

Max Activating Token Index: 855

Text #15

Max Range: 4.6076. Min Range: -4.6076

Max Act: 4.4799. Min Act: -0.1700

Data Index: 5010559 (Open Web Text)

Max Activating Token Index: 822

Text #16

Max Range: 4.6076. Min Range: -4.6076

Max Act: 4.4473. Min Act: -0.1700

Data Index: 6846539 (Open Web Text)

Max Activating Token Index: 625

Text #17

Max Range: 4.6076. Min Range: -4.6076

Max Act: 4.4466. Min Act: -0.1700

Data Index: 583655 (Open Web Text)

Max Activating Token Index: 985

Text #18

Max Range: 4.6076. Min Range: -4.6076

Max Act: 4.4712. Min Act: -0.1700

Data Index: 583656 (Open Web Text)

Max Activating Token Index: 947

Text #19

Max Range: 4.6076. Min Range: -4.6076

Max Act: 4.4814. Min Act: -0.1700

Data Index: 5010561 (Open Web Text)

Max Activating Token Index: 409