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

Dataset: Open Web Text

Neuron 1067 in Layer 3

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: 4.6252. Min Range: -4.6252

Max Act: 4.6252. Min Act: -0.1700

Data Index: 7273059 (Open Web Text)

Max Activating Token Index: 60

Text #1

Max Range: 4.6252. Min Range: -4.6252

Max Act: 4.6188. Min Act: -0.1700

Data Index: 798913 (Open Web Text)

Max Activating Token Index: 517

Text #2

Max Range: 4.6252. Min Range: -4.6252

Max Act: 4.5158. Min Act: -0.1700

Data Index: 8595040 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 4.6252. Min Range: -4.6252

Max Act: 4.4362. Min Act: -0.1700

Data Index: 6416005 (Open Web Text)

Max Activating Token Index: 613

Text #4

Max Range: 4.6252. Min Range: -4.6252

Max Act: 4.4821. Min Act: -0.1700

Data Index: 900594 (Open Web Text)

Max Activating Token Index: 576

Text #5

Max Range: 4.6252. Min Range: -4.6252

Max Act: 4.4570. Min Act: -0.1700

Data Index: 892465 (Open Web Text)

Max Activating Token Index: 693

Text #6

Max Range: 4.6252. Min Range: -4.6252

Max Act: 4.4774. Min Act: -0.1700

Data Index: 2457969 (Open Web Text)

Max Activating Token Index: 450

Text #7

Max Range: 4.6252. Min Range: -4.6252

Max Act: 4.4554. Min Act: -0.1700

Data Index: 1913675 (Open Web Text)

Max Activating Token Index: 441

Text #8

Max Range: 4.6252. Min Range: -4.6252

Max Act: 4.4492. Min Act: -0.1700

Data Index: 7282067 (Open Web Text)

Max Activating Token Index: 618

Text #9

Max Range: 4.6252. Min Range: -4.6252

Max Act: 4.4699. Min Act: -0.1700

Data Index: 546304 (Open Web Text)

Max Activating Token Index: 997

Text #10

Max Range: 4.6252. Min Range: -4.6252

Max Act: 4.4812. Min Act: -0.1700

Data Index: 6729050 (Open Web Text)

Max Activating Token Index: 1009

Text #11

Max Range: 4.6252. Min Range: -4.6252

Max Act: 4.4968. Min Act: -0.1700

Data Index: 2591434 (Open Web Text)

Max Activating Token Index: 815

Text #12

Max Range: 4.6252. Min Range: -4.6252

Max Act: 4.4448. Min Act: -0.1700

Data Index: 6695801 (Open Web Text)

Max Activating Token Index: 140

Text #13

Max Range: 4.6252. Min Range: -4.6252

Max Act: 4.4341. Min Act: -0.1700

Data Index: 6015229 (Open Web Text)

Max Activating Token Index: 577

Text #14

Max Range: 4.6252. Min Range: -4.6252

Max Act: 4.4302. Min Act: -0.1700

Data Index: 832091 (Open Web Text)

Max Activating Token Index: 123

Text #15

Max Range: 4.6252. Min Range: -4.6252

Max Act: 4.4091. Min Act: -0.1700

Data Index: 453125 (Open Web Text)

Max Activating Token Index: 674

Text #16

Max Range: 4.6252. Min Range: -4.6252

Max Act: 4.3989. Min Act: -0.1700

Data Index: 4321120 (Open Web Text)

Max Activating Token Index: 560

Text #17

Max Range: 4.6252. Min Range: -4.6252

Max Act: 4.4054. Min Act: -0.1700

Data Index: 2317198 (Open Web Text)

Max Activating Token Index: 415

Text #18

Max Range: 4.6252. Min Range: -4.6252

Max Act: 4.4213. Min Act: -0.1700

Data Index: 4381958 (Open Web Text)

Max Activating Token Index: 392

Text #19

Max Range: 4.6252. Min Range: -4.6252

Max Act: 4.4442. Min Act: -0.1700

Data Index: 4744397 (Open Web Text)

Max Activating Token Index: 586