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

Dataset: Open Web Text

Neuron 2323 in Layer 6

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: 5.5510. Min Range: -5.5510

Max Act: 5.5510. Min Act: -0.1700

Data Index: 4744480 (Open Web Text)

Max Activating Token Index: 148

Text #1

Max Range: 5.5510. Min Range: -5.5510

Max Act: 5.4362. Min Act: -0.1700

Data Index: 403535 (Open Web Text)

Max Activating Token Index: 334

Text #2

Max Range: 5.5510. Min Range: -5.5510

Max Act: 5.4031. Min Act: -0.1700

Data Index: 300569 (Open Web Text)

Max Activating Token Index: 736

Text #3

Max Range: 5.5510. Min Range: -5.5510

Max Act: 5.3283. Min Act: -0.1700

Data Index: 2823138 (Open Web Text)

Max Activating Token Index: 723

Text #4

Max Range: 5.5510. Min Range: -5.5510

Max Act: 5.3766. Min Act: -0.1700

Data Index: 4500156 (Open Web Text)

Max Activating Token Index: 112

Text #5

Max Range: 5.5510. Min Range: -5.5510

Max Act: 5.3547. Min Act: -0.1700

Data Index: 509298 (Open Web Text)

Max Activating Token Index: 978

Text #6

Max Range: 5.5510. Min Range: -5.5510

Max Act: 5.3145. Min Act: -0.1700

Data Index: 4665878 (Open Web Text)

Max Activating Token Index: 545

Text #7

Max Range: 5.5510. Min Range: -5.5510

Max Act: 5.2947. Min Act: -0.1700

Data Index: 5611278 (Open Web Text)

Max Activating Token Index: 407

Text #8

Max Range: 5.5510. Min Range: -5.5510

Max Act: 5.2992. Min Act: -0.1700

Data Index: 6609011 (Open Web Text)

Max Activating Token Index: 232

Text #9

Max Range: 5.5510. Min Range: -5.5510

Max Act: 5.2940. Min Act: -0.1700

Data Index: 5096478 (Open Web Text)

Max Activating Token Index: 214

Text #10

Max Range: 5.5510. Min Range: -5.5510

Max Act: 5.2464. Min Act: -0.1700

Data Index: 1287394 (Open Web Text)

Max Activating Token Index: 998

Text #11

Max Range: 5.5510. Min Range: -5.5510

Max Act: 5.2719. Min Act: -0.1700

Data Index: 205116 (Open Web Text)

Max Activating Token Index: 203

Text #12

Max Range: 5.5510. Min Range: -5.5510

Max Act: 5.2808. Min Act: -0.1700

Data Index: 4973588 (Open Web Text)

Max Activating Token Index: 860

Text #13

Max Range: 5.5510. Min Range: -5.5510

Max Act: 5.2402. Min Act: -0.1700

Data Index: 8674911 (Open Web Text)

Max Activating Token Index: 809

Text #14

Max Range: 5.5510. Min Range: -5.5510

Max Act: 5.2635. Min Act: -0.1700

Data Index: 8434210 (Open Web Text)

Max Activating Token Index: 311

Text #15

Max Range: 5.5510. Min Range: -5.5510

Max Act: 5.2665. Min Act: -0.1700

Data Index: 5571706 (Open Web Text)

Max Activating Token Index: 200

Text #16

Max Range: 5.5510. Min Range: -5.5510

Max Act: 5.2423. Min Act: -0.1700

Data Index: 2519704 (Open Web Text)

Max Activating Token Index: 432

Text #17

Max Range: 5.5510. Min Range: -5.5510

Max Act: 5.2021. Min Act: -0.1700

Data Index: 5558177 (Open Web Text)

Max Activating Token Index: 293

Text #18

Max Range: 5.5510. Min Range: -5.5510

Max Act: 5.2244. Min Act: -0.1700

Data Index: 1673043 (Open Web Text)

Max Activating Token Index: 517

Text #19

Max Range: 5.5510. Min Range: -5.5510

Max Act: 5.2263. Min Act: -0.1700

Data Index: 4320908 (Open Web Text)

Max Activating Token Index: 141