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

Dataset: Open Web Text

Neuron 619 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: 1.9223. Min Range: -1.9223

Max Act: 1.9223. Min Act: -0.1700

Data Index: 5501697 (Open Web Text)

Max Activating Token Index: 111

Text #1

Max Range: 1.9223. Min Range: -1.9223

Max Act: 1.8764. Min Act: -0.1700

Data Index: 8036099 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 1.9223. Min Range: -1.9223

Max Act: 1.8879. Min Act: -0.1700

Data Index: 6440612 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 1.9223. Min Range: -1.9223

Max Act: 1.8879. Min Act: -0.1700

Data Index: 2408208 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 1.9223. Min Range: -1.9223

Max Act: 1.8879. Min Act: -0.1700

Data Index: 1609384 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 1.9223. Min Range: -1.9223

Max Act: 1.8764. Min Act: -0.1700

Data Index: 6558490 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.9223. Min Range: -1.9223

Max Act: 1.8879. Min Act: -0.1700

Data Index: 2008179 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 1.9223. Min Range: -1.9223

Max Act: 1.8879. Min Act: -0.1700

Data Index: 8335098 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 1.9223. Min Range: -1.9223

Max Act: 1.8764. Min Act: -0.1700

Data Index: 6949101 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 1.9223. Min Range: -1.9223

Max Act: 1.8879. Min Act: -0.1700

Data Index: 608069 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 1.9223. Min Range: -1.9223

Max Act: 1.8879. Min Act: -0.1700

Data Index: 8409091 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 1.9223. Min Range: -1.9223

Max Act: 1.8764. Min Act: -0.1700

Data Index: 7960161 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 1.9223. Min Range: -1.9223

Max Act: 1.8612. Min Act: -0.1700

Data Index: 217783 (Open Web Text)

Max Activating Token Index: 609

Text #13

Max Range: 1.9223. Min Range: -1.9223

Max Act: 1.8537. Min Act: -0.1700

Data Index: 2457153 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 1.9223. Min Range: -1.9223

Max Act: 1.8440. Min Act: -0.1700

Data Index: 4408398 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 1.9223. Min Range: -1.9223

Max Act: 1.8541. Min Act: -0.1700

Data Index: 3834647 (Open Web Text)

Max Activating Token Index: 240

Text #16

Max Range: 1.9223. Min Range: -1.9223

Max Act: 1.8448. Min Act: -0.1700

Data Index: 3258352 (Open Web Text)

Max Activating Token Index: 92

Text #17

Max Range: 1.9223. Min Range: -1.9223

Max Act: 1.8513. Min Act: -0.1700

Data Index: 8078110 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 1.9223. Min Range: -1.9223

Max Act: 1.8442. Min Act: -0.1700

Data Index: 2262395 (Open Web Text)

Max Activating Token Index: 616

Text #19

Max Range: 1.9223. Min Range: -1.9223

Max Act: 1.8251. Min Act: -0.1700

Data Index: 2395395 (Open Web Text)

Max Activating Token Index: 163