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

Dataset: Open Web Text

Neuron 1284 in Layer 3

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: 4.1140. Min Range: -4.1140

Max Act: 4.1140. Min Act: -0.1700

Data Index: 5086903 (Open Web Text)

Max Activating Token Index: 413

Text #1

Max Range: 4.1140. Min Range: -4.1140

Max Act: 4.0125. Min Act: -0.1700

Data Index: 2686273 (Open Web Text)

Max Activating Token Index: 163

Text #2

Max Range: 4.1140. Min Range: -4.1140

Max Act: 3.9949. Min Act: -0.1700

Data Index: 7873324 (Open Web Text)

Max Activating Token Index: 896

Text #3

Max Range: 4.1140. Min Range: -4.1140

Max Act: 3.9783. Min Act: -0.1700

Data Index: 6817237 (Open Web Text)

Max Activating Token Index: 649

Text #4

Max Range: 4.1140. Min Range: -4.1140

Max Act: 3.9708. Min Act: -0.1700

Data Index: 6432101 (Open Web Text)

Max Activating Token Index: 334

Text #5

Max Range: 4.1140. Min Range: -4.1140

Max Act: 3.9330. Min Act: -0.1700

Data Index: 3415212 (Open Web Text)

Max Activating Token Index: 482

Text #6

Max Range: 4.1140. Min Range: -4.1140

Max Act: 3.9394. Min Act: -0.1700

Data Index: 4206248 (Open Web Text)

Max Activating Token Index: 688

Text #7

Max Range: 4.1140. Min Range: -4.1140

Max Act: 3.9427. Min Act: -0.1700

Data Index: 1425380 (Open Web Text)

Max Activating Token Index: 964

Text #8

Max Range: 4.1140. Min Range: -4.1140

Max Act: 3.9455. Min Act: -0.1700

Data Index: 3023116 (Open Web Text)

Max Activating Token Index: 238

Text #9

Max Range: 4.1140. Min Range: -4.1140

Max Act: 3.9033. Min Act: -0.1700

Data Index: 1739515 (Open Web Text)

Max Activating Token Index: 447

Text #10

Max Range: 4.1140. Min Range: -4.1140

Max Act: 3.9115. Min Act: -0.1700

Data Index: 2531278 (Open Web Text)

Max Activating Token Index: 596

Text #11

Max Range: 4.1140. Min Range: -4.1140

Max Act: 3.8988. Min Act: -0.1700

Data Index: 6514802 (Open Web Text)

Max Activating Token Index: 424

Text #12

Max Range: 4.1140. Min Range: -4.1140

Max Act: 3.8900. Min Act: -0.1700

Data Index: 6354939 (Open Web Text)

Max Activating Token Index: 1020

Text #13

Max Range: 4.1140. Min Range: -4.1140

Max Act: 3.9040. Min Act: -0.1700

Data Index: 7392960 (Open Web Text)

Max Activating Token Index: 988

Text #14

Max Range: 4.1140. Min Range: -4.1140

Max Act: 3.9056. Min Act: -0.1700

Data Index: 202987 (Open Web Text)

Max Activating Token Index: 999

Text #15

Max Range: 4.1140. Min Range: -4.1140

Max Act: 3.9111. Min Act: -0.1700

Data Index: 191405 (Open Web Text)

Max Activating Token Index: 403

Text #16

Max Range: 4.1140. Min Range: -4.1140

Max Act: 3.9248. Min Act: -0.1700

Data Index: 421832 (Open Web Text)

Max Activating Token Index: 107

Text #17

Max Range: 4.1140. Min Range: -4.1140

Max Act: 3.9131. Min Act: -0.1700

Data Index: 5947133 (Open Web Text)

Max Activating Token Index: 686

Text #18

Max Range: 4.1140. Min Range: -4.1140

Max Act: 3.9201. Min Act: -0.1700

Data Index: 4702361 (Open Web Text)

Max Activating Token Index: 192

Text #19

Max Range: 4.1140. Min Range: -4.1140

Max Act: 3.8873. Min Act: -0.1700

Data Index: 4299981 (Open Web Text)

Max Activating Token Index: 337