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

Dataset: Open Web Text

Neuron 2169 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: 2.4219. Min Range: -2.4219

Max Act: 2.4219. Min Act: -0.1700

Data Index: 7080958 (Open Web Text)

Max Activating Token Index: 418

Text #1

Max Range: 2.4219. Min Range: -2.4219

Max Act: 2.3986. Min Act: -0.1700

Data Index: 7272784 (Open Web Text)

Max Activating Token Index: 824

Text #2

Max Range: 2.4219. Min Range: -2.4219

Max Act: 2.3327. Min Act: -0.1700

Data Index: 974584 (Open Web Text)

Max Activating Token Index: 770

Text #3

Max Range: 2.4219. Min Range: -2.4219

Max Act: 2.3332. Min Act: -0.1700

Data Index: 1460597 (Open Web Text)

Max Activating Token Index: 623

Text #4

Max Range: 2.4219. Min Range: -2.4219

Max Act: 2.3171. Min Act: -0.1700

Data Index: 3261369 (Open Web Text)

Max Activating Token Index: 624

Text #5

Max Range: 2.4219. Min Range: -2.4219

Max Act: 2.3131. Min Act: -0.1700

Data Index: 1849118 (Open Web Text)

Max Activating Token Index: 214

Text #6

Max Range: 2.4219. Min Range: -2.4219

Max Act: 2.2937. Min Act: -0.1700

Data Index: 7348422 (Open Web Text)

Max Activating Token Index: 251

Text #7

Max Range: 2.4219. Min Range: -2.4219

Max Act: 2.2935. Min Act: -0.1700

Data Index: 5701944 (Open Web Text)

Max Activating Token Index: 513

Text #8

Max Range: 2.4219. Min Range: -2.4219

Max Act: 2.3024. Min Act: -0.1700

Data Index: 7134285 (Open Web Text)

Max Activating Token Index: 282

Text #9

Max Range: 2.4219. Min Range: -2.4219

Max Act: 2.3088. Min Act: -0.1700

Data Index: 1697166 (Open Web Text)

Max Activating Token Index: 130

Text #10

Max Range: 2.4219. Min Range: -2.4219

Max Act: 2.3199. Min Act: -0.1700

Data Index: 4298393 (Open Web Text)

Max Activating Token Index: 578

Text #11

Max Range: 2.4219. Min Range: -2.4219

Max Act: 2.3089. Min Act: -0.1700

Data Index: 2413121 (Open Web Text)

Max Activating Token Index: 275

Text #12

Max Range: 2.4219. Min Range: -2.4219

Max Act: 2.2869. Min Act: -0.1700

Data Index: 7645526 (Open Web Text)

Max Activating Token Index: 48

Text #13

Max Range: 2.4219. Min Range: -2.4219

Max Act: 2.2674. Min Act: -0.1700

Data Index: 1227723 (Open Web Text)

Max Activating Token Index: 775

Text #14

Max Range: 2.4219. Min Range: -2.4219

Max Act: 2.2758. Min Act: -0.1700

Data Index: 2102916 (Open Web Text)

Max Activating Token Index: 229

Text #15

Max Range: 2.4219. Min Range: -2.4219

Max Act: 2.2661. Min Act: -0.1700

Data Index: 8215930 (Open Web Text)

Max Activating Token Index: 48

Text #16

Max Range: 2.4219. Min Range: -2.4219

Max Act: 2.2838. Min Act: -0.1700

Data Index: 5446926 (Open Web Text)

Max Activating Token Index: 492

Text #17

Max Range: 2.4219. Min Range: -2.4219

Max Act: 2.2822. Min Act: -0.1700

Data Index: 2178418 (Open Web Text)

Max Activating Token Index: 47

Text #18

Max Range: 2.4219. Min Range: -2.4219

Max Act: 2.2769. Min Act: -0.1700

Data Index: 8491124 (Open Web Text)

Max Activating Token Index: 513

Text #19

Max Range: 2.4219. Min Range: -2.4219

Max Act: 2.2504. Min Act: -0.1700

Data Index: 6212077 (Open Web Text)

Max Activating Token Index: 749