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

Dataset: Open Web Text

Neuron 2787 in Layer 5

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: 5.2700. Min Range: -5.2700

Max Act: 5.2700. Min Act: -0.1700

Data Index: 4777061 (Open Web Text)

Max Activating Token Index: 441

Text #1

Max Range: 5.2700. Min Range: -5.2700

Max Act: 4.9287. Min Act: -0.1700

Data Index: 7734873 (Open Web Text)

Max Activating Token Index: 521

Text #2

Max Range: 5.2700. Min Range: -5.2700

Max Act: 4.9010. Min Act: -0.1700

Data Index: 950569 (Open Web Text)

Max Activating Token Index: 250

Text #3

Max Range: 5.2700. Min Range: -5.2700

Max Act: 4.8733. Min Act: -0.1700

Data Index: 6338721 (Open Web Text)

Max Activating Token Index: 105

Text #4

Max Range: 5.2700. Min Range: -5.2700

Max Act: 4.8772. Min Act: -0.1700

Data Index: 577507 (Open Web Text)

Max Activating Token Index: 684

Text #5

Max Range: 5.2700. Min Range: -5.2700

Max Act: 4.8595. Min Act: -0.1700

Data Index: 6125533 (Open Web Text)

Max Activating Token Index: 40

Text #6

Max Range: 5.2700. Min Range: -5.2700

Max Act: 4.8437. Min Act: -0.1700

Data Index: 2382632 (Open Web Text)

Max Activating Token Index: 789

Text #7

Max Range: 5.2700. Min Range: -5.2700

Max Act: 4.8358. Min Act: -0.1700

Data Index: 4808688 (Open Web Text)

Max Activating Token Index: 325

Text #8

Max Range: 5.2700. Min Range: -5.2700

Max Act: 4.7622. Min Act: -0.1700

Data Index: 2351524 (Open Web Text)

Max Activating Token Index: 761

Text #9

Max Range: 5.2700. Min Range: -5.2700

Max Act: 4.8051. Min Act: -0.1700

Data Index: 372282 (Open Web Text)

Max Activating Token Index: 217

Text #10

Max Range: 5.2700. Min Range: -5.2700

Max Act: 4.8082. Min Act: -0.1700

Data Index: 2662720 (Open Web Text)

Max Activating Token Index: 619

Text #11

Max Range: 5.2700. Min Range: -5.2700

Max Act: 4.7948. Min Act: -0.1700

Data Index: 67805 (Open Web Text)

Max Activating Token Index: 103

Text #12

Max Range: 5.2700. Min Range: -5.2700

Max Act: 4.8307. Min Act: -0.1700

Data Index: 6041334 (Open Web Text)

Max Activating Token Index: 762

Text #13

Max Range: 5.2700. Min Range: -5.2700

Max Act: 4.7847. Min Act: -0.1700

Data Index: 6113609 (Open Web Text)

Max Activating Token Index: 953

Text #14

Max Range: 5.2700. Min Range: -5.2700

Max Act: 4.7900. Min Act: -0.1700

Data Index: 1607184 (Open Web Text)

Max Activating Token Index: 415

Text #15

Max Range: 5.2700. Min Range: -5.2700

Max Act: 4.7827. Min Act: -0.1700

Data Index: 3538589 (Open Web Text)

Max Activating Token Index: 231

Text #16

Max Range: 5.2700. Min Range: -5.2700

Max Act: 4.7946. Min Act: -0.1700

Data Index: 2825042 (Open Web Text)

Max Activating Token Index: 180

Text #17

Max Range: 5.2700. Min Range: -5.2700

Max Act: 4.7200. Min Act: -0.1700

Data Index: 2930848 (Open Web Text)

Max Activating Token Index: 474

Text #18

Max Range: 5.2700. Min Range: -5.2700

Max Act: 4.8428. Min Act: -0.1700

Data Index: 6202332 (Open Web Text)

Max Activating Token Index: 427

Text #19

Max Range: 5.2700. Min Range: -5.2700

Max Act: 4.7908. Min Act: -0.1700

Data Index: 4646149 (Open Web Text)

Max Activating Token Index: 245