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

Dataset: Open Web Text

Neuron 2284 in Layer 2

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: 3.1942. Min Range: -3.1942

Max Act: 3.1942. Min Act: -0.1700

Data Index: 8675896 (Open Web Text)

Max Activating Token Index: 426

Text #1

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.1713. Min Act: -0.1700

Data Index: 5370423 (Open Web Text)

Max Activating Token Index: 352

Text #2

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.1712. Min Act: -0.1700

Data Index: 4259563 (Open Web Text)

Max Activating Token Index: 466

Text #3

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.1438. Min Act: -0.1700

Data Index: 499283 (Open Web Text)

Max Activating Token Index: 916

Text #4

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.1309. Min Act: -0.1700

Data Index: 5192765 (Open Web Text)

Max Activating Token Index: 243

Text #5

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.1201. Min Act: -0.1700

Data Index: 6899800 (Open Web Text)

Max Activating Token Index: 857

Text #6

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.1334. Min Act: -0.1700

Data Index: 3479863 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.0998. Min Act: -0.1700

Data Index: 129578 (Open Web Text)

Max Activating Token Index: 546

Text #8

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.1241. Min Act: -0.1700

Data Index: 419156 (Open Web Text)

Max Activating Token Index: 693

Text #9

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.1157. Min Act: -0.1700

Data Index: 4410266 (Open Web Text)

Max Activating Token Index: 697

Text #10

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.1126. Min Act: -0.1700

Data Index: 4392872 (Open Web Text)

Max Activating Token Index: 357

Text #11

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.1106. Min Act: -0.1700

Data Index: 6587708 (Open Web Text)

Max Activating Token Index: 302

Text #12

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.1118. Min Act: -0.1700

Data Index: 6099349 (Open Web Text)

Max Activating Token Index: 69

Text #13

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.1321. Min Act: -0.1700

Data Index: 7155856 (Open Web Text)

Max Activating Token Index: 254

Text #14

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.0997. Min Act: -0.1700

Data Index: 5041733 (Open Web Text)

Max Activating Token Index: 665

Text #15

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.0946. Min Act: -0.1700

Data Index: 3773232 (Open Web Text)

Max Activating Token Index: 842

Text #16

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.1137. Min Act: -0.1700

Data Index: 2451743 (Open Web Text)

Max Activating Token Index: 808

Text #17

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.0952. Min Act: -0.1700

Data Index: 5552156 (Open Web Text)

Max Activating Token Index: 348

Text #18

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.0950. Min Act: -0.1700

Data Index: 290988 (Open Web Text)

Max Activating Token Index: 417

Text #19

Max Range: 3.1942. Min Range: -3.1942

Max Act: 3.0989. Min Act: -0.1700

Data Index: 218372 (Open Web Text)

Max Activating Token Index: 150