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

Dataset: Open Web Text

Neuron 345 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: 3.4560. Min Range: -3.4560

Max Act: 3.4560. Min Act: -0.1700

Data Index: 619726 (Open Web Text)

Max Activating Token Index: 574

Text #1

Max Range: 3.4560. Min Range: -3.4560

Max Act: 3.3426. Min Act: -0.1700

Data Index: 6265407 (Open Web Text)

Max Activating Token Index: 203

Text #2

Max Range: 3.4560. Min Range: -3.4560

Max Act: 3.3197. Min Act: -0.1700

Data Index: 5633993 (Open Web Text)

Max Activating Token Index: 490

Text #3

Max Range: 3.4560. Min Range: -3.4560

Max Act: 3.2922. Min Act: -0.1700

Data Index: 3280516 (Open Web Text)

Max Activating Token Index: 478

Text #4

Max Range: 3.4560. Min Range: -3.4560

Max Act: 3.2932. Min Act: -0.1700

Data Index: 5838846 (Open Web Text)

Max Activating Token Index: 48

Text #5

Max Range: 3.4560. Min Range: -3.4560

Max Act: 3.3113. Min Act: -0.1700

Data Index: 3447530 (Open Web Text)

Max Activating Token Index: 793

Text #6

Max Range: 3.4560. Min Range: -3.4560

Max Act: 3.2887. Min Act: -0.1700

Data Index: 7435845 (Open Web Text)

Max Activating Token Index: 175

Text #7

Max Range: 3.4560. Min Range: -3.4560

Max Act: 3.2687. Min Act: -0.1700

Data Index: 1946929 (Open Web Text)

Max Activating Token Index: 431

Text #8

Max Range: 3.4560. Min Range: -3.4560

Max Act: 3.2567. Min Act: -0.1700

Data Index: 3239419 (Open Web Text)

Max Activating Token Index: 869

Text #9

Max Range: 3.4560. Min Range: -3.4560

Max Act: 3.2462. Min Act: -0.1700

Data Index: 7426066 (Open Web Text)

Max Activating Token Index: 276

Text #10

Max Range: 3.4560. Min Range: -3.4560

Max Act: 3.2523. Min Act: -0.1700

Data Index: 3986561 (Open Web Text)

Max Activating Token Index: 103

Text #11

Max Range: 3.4560. Min Range: -3.4560

Max Act: 3.2282. Min Act: -0.1700

Data Index: 1692254 (Open Web Text)

Max Activating Token Index: 400

Text #12

Max Range: 3.4560. Min Range: -3.4560

Max Act: 3.2479. Min Act: -0.1700

Data Index: 348544 (Open Web Text)

Max Activating Token Index: 523

Text #13

Max Range: 3.4560. Min Range: -3.4560

Max Act: 3.2710. Min Act: -0.1700

Data Index: 146713 (Open Web Text)

Max Activating Token Index: 897

Text #14

Max Range: 3.4560. Min Range: -3.4560

Max Act: 3.2171. Min Act: -0.1700

Data Index: 1305168 (Open Web Text)

Max Activating Token Index: 327

Text #15

Max Range: 3.4560. Min Range: -3.4560

Max Act: 3.2028. Min Act: -0.1700

Data Index: 470214 (Open Web Text)

Max Activating Token Index: 593

Text #16

Max Range: 3.4560. Min Range: -3.4560

Max Act: 3.2088. Min Act: -0.1700

Data Index: 2322229 (Open Web Text)

Max Activating Token Index: 250

Text #17

Max Range: 3.4560. Min Range: -3.4560

Max Act: 3.2016. Min Act: -0.1700

Data Index: 1655754 (Open Web Text)

Max Activating Token Index: 209

Text #18

Max Range: 3.4560. Min Range: -3.4560

Max Act: 3.2013. Min Act: -0.1700

Data Index: 465429 (Open Web Text)

Max Activating Token Index: 914

Text #19

Max Range: 3.4560. Min Range: -3.4560

Max Act: 3.2021. Min Act: -0.1700

Data Index: 4872777 (Open Web Text)

Max Activating Token Index: 848