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

Dataset: Open Web Text

Neuron 2690 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: 6.0428. Min Range: -6.0428

Max Act: 6.0428. Min Act: -0.1700

Data Index: 5332186 (Open Web Text)

Max Activating Token Index: 67

Text #1

Max Range: 6.0428. Min Range: -6.0428

Max Act: 6.0312. Min Act: -0.1699

Data Index: 8663804 (Open Web Text)

Max Activating Token Index: 719

Text #2

Max Range: 6.0428. Min Range: -6.0428

Max Act: 5.8510. Min Act: -0.1700

Data Index: 313256 (Open Web Text)

Max Activating Token Index: 473

Text #3

Max Range: 6.0428. Min Range: -6.0428

Max Act: 5.8613. Min Act: -0.1700

Data Index: 8649972 (Open Web Text)

Max Activating Token Index: 141

Text #4

Max Range: 6.0428. Min Range: -6.0428

Max Act: 5.8827. Min Act: -0.1700

Data Index: 3787345 (Open Web Text)

Max Activating Token Index: 516

Text #5

Max Range: 6.0428. Min Range: -6.0428

Max Act: 5.8337. Min Act: -0.1700

Data Index: 8335095 (Open Web Text)

Max Activating Token Index: 651

Text #6

Max Range: 6.0428. Min Range: -6.0428

Max Act: 5.8063. Min Act: -0.1700

Data Index: 5105278 (Open Web Text)

Max Activating Token Index: 988

Text #7

Max Range: 6.0428. Min Range: -6.0428

Max Act: 5.8514. Min Act: -0.1700

Data Index: 5184661 (Open Web Text)

Max Activating Token Index: 428

Text #8

Max Range: 6.0428. Min Range: -6.0428

Max Act: 5.8001. Min Act: -0.1699

Data Index: 6019438 (Open Web Text)

Max Activating Token Index: 1018

Text #9

Max Range: 6.0428. Min Range: -6.0428

Max Act: 5.7773. Min Act: -0.1700

Data Index: 912875 (Open Web Text)

Max Activating Token Index: 321

Text #10

Max Range: 6.0428. Min Range: -6.0428

Max Act: 5.7391. Min Act: -0.1700

Data Index: 192492 (Open Web Text)

Max Activating Token Index: 786

Text #11

Max Range: 6.0428. Min Range: -6.0428

Max Act: 5.7761. Min Act: -0.1700

Data Index: 2575886 (Open Web Text)

Max Activating Token Index: 217

Text #12

Max Range: 6.0428. Min Range: -6.0428

Max Act: 5.7737. Min Act: -0.1700

Data Index: 7962684 (Open Web Text)

Max Activating Token Index: 342

Text #13

Max Range: 6.0428. Min Range: -6.0428

Max Act: 5.7892. Min Act: -0.1700

Data Index: 4567400 (Open Web Text)

Max Activating Token Index: 160

Text #14

Max Range: 6.0428. Min Range: -6.0428

Max Act: 5.6900. Min Act: -0.1700

Data Index: 3820916 (Open Web Text)

Max Activating Token Index: 893

Text #15

Max Range: 6.0428. Min Range: -6.0428

Max Act: 5.7244. Min Act: -0.1700

Data Index: 3829908 (Open Web Text)

Max Activating Token Index: 936

Text #16

Max Range: 6.0428. Min Range: -6.0428

Max Act: 5.7149. Min Act: -0.1700

Data Index: 1324529 (Open Web Text)

Max Activating Token Index: 876

Text #17

Max Range: 6.0428. Min Range: -6.0428

Max Act: 5.7353. Min Act: -0.1700

Data Index: 7629902 (Open Web Text)

Max Activating Token Index: 509

Text #18

Max Range: 6.0428. Min Range: -6.0428

Max Act: 5.6804. Min Act: -0.1700

Data Index: 3968104 (Open Web Text)

Max Activating Token Index: 900

Text #19

Max Range: 6.0428. Min Range: -6.0428

Max Act: 5.6953. Min Act: -0.1700

Data Index: 8071824 (Open Web Text)

Max Activating Token Index: 608