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

Dataset: Open Web Text

Neuron 1793 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: 5.3657. Min Range: -5.3657

Max Act: 5.3657. Min Act: -0.1700

Data Index: 8134836 (Open Web Text)

Max Activating Token Index: 342

Text #1

Max Range: 5.3657. Min Range: -5.3657

Max Act: 5.2932. Min Act: -0.1700

Data Index: 6982770 (Open Web Text)

Max Activating Token Index: 77

Text #2

Max Range: 5.3657. Min Range: -5.3657

Max Act: 5.2599. Min Act: -0.1700

Data Index: 5596592 (Open Web Text)

Max Activating Token Index: 593

Text #3

Max Range: 5.3657. Min Range: -5.3657

Max Act: 5.0529. Min Act: -0.1700

Data Index: 2300113 (Open Web Text)

Max Activating Token Index: 897

Text #4

Max Range: 5.3657. Min Range: -5.3657

Max Act: 5.0264. Min Act: -0.1700

Data Index: 5627681 (Open Web Text)

Max Activating Token Index: 680

Text #5

Max Range: 5.3657. Min Range: -5.3657

Max Act: 4.9969. Min Act: -0.1700

Data Index: 4667193 (Open Web Text)

Max Activating Token Index: 402

Text #6

Max Range: 5.3657. Min Range: -5.3657

Max Act: 4.9996. Min Act: -0.1700

Data Index: 2634585 (Open Web Text)

Max Activating Token Index: 124

Text #7

Max Range: 5.3657. Min Range: -5.3657

Max Act: 4.9863. Min Act: -0.1700

Data Index: 8313701 (Open Web Text)

Max Activating Token Index: 464

Text #8

Max Range: 5.3657. Min Range: -5.3657

Max Act: 4.9736. Min Act: -0.1700

Data Index: 6079051 (Open Web Text)

Max Activating Token Index: 545

Text #9

Max Range: 5.3657. Min Range: -5.3657

Max Act: 4.9734. Min Act: -0.1700

Data Index: 4560119 (Open Web Text)

Max Activating Token Index: 72

Text #10

Max Range: 5.3657. Min Range: -5.3657

Max Act: 4.9546. Min Act: -0.1700

Data Index: 6353364 (Open Web Text)

Max Activating Token Index: 322

Text #11

Max Range: 5.3657. Min Range: -5.3657

Max Act: 4.9318. Min Act: -0.1700

Data Index: 2767110 (Open Web Text)

Max Activating Token Index: 752

Text #12

Max Range: 5.3657. Min Range: -5.3657

Max Act: 4.9519. Min Act: -0.1700

Data Index: 7201252 (Open Web Text)

Max Activating Token Index: 229

Text #13

Max Range: 5.3657. Min Range: -5.3657

Max Act: 4.9111. Min Act: -0.1700

Data Index: 7502657 (Open Web Text)

Max Activating Token Index: 398

Text #14

Max Range: 5.3657. Min Range: -5.3657

Max Act: 4.8951. Min Act: -0.1700

Data Index: 7145973 (Open Web Text)

Max Activating Token Index: 302

Text #15

Max Range: 5.3657. Min Range: -5.3657

Max Act: 4.8853. Min Act: -0.1700

Data Index: 5077628 (Open Web Text)

Max Activating Token Index: 222

Text #16

Max Range: 5.3657. Min Range: -5.3657

Max Act: 4.9174. Min Act: -0.1700

Data Index: 3060661 (Open Web Text)

Max Activating Token Index: 996

Text #17

Max Range: 5.3657. Min Range: -5.3657

Max Act: 4.9126. Min Act: -0.1700

Data Index: 4146154 (Open Web Text)

Max Activating Token Index: 177

Text #18

Max Range: 5.3657. Min Range: -5.3657

Max Act: 4.9031. Min Act: -0.1700

Data Index: 4913270 (Open Web Text)

Max Activating Token Index: 435

Text #19

Max Range: 5.3657. Min Range: -5.3657

Max Act: 4.9113. Min Act: -0.1700

Data Index: 1900400 (Open Web Text)

Max Activating Token Index: 477