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

Dataset: Open Web Text

Neuron 645 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: 3.8409. Min Range: -3.8409

Max Act: 3.8398. Min Act: -0.1700

Data Index: 8524073 (Open Web Text)

Max Activating Token Index: 569

Text #1

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.8284. Min Act: -0.1700

Data Index: 797072 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.8178. Min Act: -0.1700

Data Index: 5068811 (Open Web Text)

Max Activating Token Index: 55

Text #3

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.8409. Min Act: -0.1700

Data Index: 4929113 (Open Web Text)

Max Activating Token Index: 124

Text #4

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.8099. Min Act: -0.1700

Data Index: 8556125 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.8033. Min Act: -0.1700

Data Index: 3842009 (Open Web Text)

Max Activating Token Index: 1014

Text #6

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.8244. Min Act: -0.1700

Data Index: 8344151 (Open Web Text)

Max Activating Token Index: 168

Text #7

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.7731. Min Act: -0.1700

Data Index: 2063853 (Open Web Text)

Max Activating Token Index: 218

Text #8

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.7893. Min Act: -0.1700

Data Index: 3995904 (Open Web Text)

Max Activating Token Index: 111

Text #9

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.7850. Min Act: -0.1700

Data Index: 6498153 (Open Web Text)

Max Activating Token Index: 87

Text #10

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.7794. Min Act: -0.1700

Data Index: 784445 (Open Web Text)

Max Activating Token Index: 362

Text #11

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.7532. Min Act: -0.1700

Data Index: 4584884 (Open Web Text)

Max Activating Token Index: 403

Text #12

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.7559. Min Act: -0.1700

Data Index: 5859464 (Open Web Text)

Max Activating Token Index: 163

Text #13

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.7467. Min Act: -0.1700

Data Index: 6449431 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.7576. Min Act: -0.1700

Data Index: 6643465 (Open Web Text)

Max Activating Token Index: 131

Text #15

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.7692. Min Act: -0.1700

Data Index: 3054008 (Open Web Text)

Max Activating Token Index: 277

Text #16

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.7576. Min Act: -0.1700

Data Index: 6976440 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.7480. Min Act: -0.1700

Data Index: 3136597 (Open Web Text)

Max Activating Token Index: 176

Text #18

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.7586. Min Act: -0.1700

Data Index: 3149262 (Open Web Text)

Max Activating Token Index: 130

Text #19

Max Range: 3.8409. Min Range: -3.8409

Max Act: 3.7478. Min Act: -0.1700

Data Index: 3378063 (Open Web Text)

Max Activating Token Index: 269