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

Dataset: Open Web Text

Neuron 2973 in Layer 4

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: 5.1064. Min Range: -5.1064

Max Act: 5.1064. Min Act: -0.1700

Data Index: 5867321 (Open Web Text)

Max Activating Token Index: 673

Text #1

Max Range: 5.1064. Min Range: -5.1064

Max Act: 4.9625. Min Act: -0.1700

Data Index: 7739649 (Open Web Text)

Max Activating Token Index: 207

Text #2

Max Range: 5.1064. Min Range: -5.1064

Max Act: 4.9210. Min Act: -0.1700

Data Index: 3476627 (Open Web Text)

Max Activating Token Index: 540

Text #3

Max Range: 5.1064. Min Range: -5.1064

Max Act: 4.9660. Min Act: -0.1700

Data Index: 8117537 (Open Web Text)

Max Activating Token Index: 517

Text #4

Max Range: 5.1064. Min Range: -5.1064

Max Act: 4.8949. Min Act: -0.1700

Data Index: 5486615 (Open Web Text)

Max Activating Token Index: 542

Text #5

Max Range: 5.1064. Min Range: -5.1064

Max Act: 4.9229. Min Act: -0.1700

Data Index: 4140370 (Open Web Text)

Max Activating Token Index: 417

Text #6

Max Range: 5.1064. Min Range: -5.1064

Max Act: 4.8766. Min Act: -0.1700

Data Index: 5047433 (Open Web Text)

Max Activating Token Index: 520

Text #7

Max Range: 5.1064. Min Range: -5.1064

Max Act: 4.8240. Min Act: -0.1700

Data Index: 3410551 (Open Web Text)

Max Activating Token Index: 846

Text #8

Max Range: 5.1064. Min Range: -5.1064

Max Act: 4.8286. Min Act: -0.1700

Data Index: 5419640 (Open Web Text)

Max Activating Token Index: 686

Text #9

Max Range: 5.1064. Min Range: -5.1064

Max Act: 4.8193. Min Act: -0.1700

Data Index: 5705534 (Open Web Text)

Max Activating Token Index: 429

Text #10

Max Range: 5.1064. Min Range: -5.1064

Max Act: 4.8091. Min Act: -0.1700

Data Index: 3735594 (Open Web Text)

Max Activating Token Index: 960

Text #11

Max Range: 5.1064. Min Range: -5.1064

Max Act: 4.8125. Min Act: -0.1700

Data Index: 1395325 (Open Web Text)

Max Activating Token Index: 206

Text #12

Max Range: 5.1064. Min Range: -5.1064

Max Act: 4.7911. Min Act: -0.1700

Data Index: 4216848 (Open Web Text)

Max Activating Token Index: 291

Text #13

Max Range: 5.1064. Min Range: -5.1064

Max Act: 4.7858. Min Act: -0.1700

Data Index: 3364590 (Open Web Text)

Max Activating Token Index: 438

Text #14

Max Range: 5.1064. Min Range: -5.1064

Max Act: 4.7768. Min Act: -0.1700

Data Index: 2057633 (Open Web Text)

Max Activating Token Index: 505

Text #15

Max Range: 5.1064. Min Range: -5.1064

Max Act: 4.7660. Min Act: -0.1700

Data Index: 7785098 (Open Web Text)

Max Activating Token Index: 130

Text #16

Max Range: 5.1064. Min Range: -5.1064

Max Act: 4.8170. Min Act: -0.1700

Data Index: 6676237 (Open Web Text)

Max Activating Token Index: 802

Text #17

Max Range: 5.1064. Min Range: -5.1064

Max Act: 4.7994. Min Act: -0.1700

Data Index: 313205 (Open Web Text)

Max Activating Token Index: 309

Text #18

Max Range: 5.1064. Min Range: -5.1064

Max Act: 4.7993. Min Act: -0.1700

Data Index: 4828283 (Open Web Text)

Max Activating Token Index: 962

Text #19

Max Range: 5.1064. Min Range: -5.1064

Max Act: 4.7724. Min Act: -0.1700

Data Index: 3447376 (Open Web Text)

Max Activating Token Index: 938