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

Dataset: Open Web Text

Neuron 2291 in Layer 1

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: 1.7188. Min Range: -1.7188

Max Act: 1.7188. Min Act: -0.1700

Data Index: 5758567 (Open Web Text)

Max Activating Token Index: 990

Text #1

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.7047. Min Act: -0.1700

Data Index: 7272659 (Open Web Text)

Max Activating Token Index: 779

Text #2

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.7084. Min Act: -0.1700

Data Index: 1837305 (Open Web Text)

Max Activating Token Index: 141

Text #3

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.7074. Min Act: -0.1700

Data Index: 1789608 (Open Web Text)

Max Activating Token Index: 352

Text #4

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.7029. Min Act: -0.1700

Data Index: 7240615 (Open Web Text)

Max Activating Token Index: 121

Text #5

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.6914. Min Act: -0.1700

Data Index: 4978533 (Open Web Text)

Max Activating Token Index: 421

Text #6

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.6874. Min Act: -0.1700

Data Index: 1859901 (Open Web Text)

Max Activating Token Index: 804

Text #7

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.6946. Min Act: -0.1700

Data Index: 2330436 (Open Web Text)

Max Activating Token Index: 917

Text #8

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.6943. Min Act: -0.1700

Data Index: 1527371 (Open Web Text)

Max Activating Token Index: 893

Text #9

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.6796. Min Act: -0.1699

Data Index: 8545168 (Open Web Text)

Max Activating Token Index: 680

Text #10

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.6893. Min Act: -0.1700

Data Index: 6443527 (Open Web Text)

Max Activating Token Index: 222

Text #11

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.6725. Min Act: -0.1700

Data Index: 1200669 (Open Web Text)

Max Activating Token Index: 109

Text #12

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.6790. Min Act: -0.1700

Data Index: 7554017 (Open Web Text)

Max Activating Token Index: 958

Text #13

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.6826. Min Act: -0.1700

Data Index: 7440370 (Open Web Text)

Max Activating Token Index: 717

Text #14

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.6719. Min Act: -0.1700

Data Index: 2523630 (Open Web Text)

Max Activating Token Index: 683

Text #15

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.6746. Min Act: -0.1700

Data Index: 867038 (Open Web Text)

Max Activating Token Index: 423

Text #16

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.6744. Min Act: -0.1700

Data Index: 7808953 (Open Web Text)

Max Activating Token Index: 454

Text #17

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.6672. Min Act: -0.1700

Data Index: 7989175 (Open Web Text)

Max Activating Token Index: 86

Text #18

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.6686. Min Act: -0.1700

Data Index: 772505 (Open Web Text)

Max Activating Token Index: 730

Text #19

Max Range: 1.7188. Min Range: -1.7188

Max Act: 1.6674. Min Act: -0.1700

Data Index: 2236648 (Open Web Text)

Max Activating Token Index: 356