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

Dataset: Open Web Text

Neuron 2229 in Layer 5

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: 5.5053. Min Range: -5.5053

Max Act: 5.5053. Min Act: -0.1700

Data Index: 3368668 (Open Web Text)

Max Activating Token Index: 525

Text #1

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.4597. Min Act: -0.1700

Data Index: 1469517 (Open Web Text)

Max Activating Token Index: 39

Text #2

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.3620. Min Act: -0.1700

Data Index: 5156607 (Open Web Text)

Max Activating Token Index: 161

Text #3

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.3271. Min Act: -0.1700

Data Index: 469704 (Open Web Text)

Max Activating Token Index: 44

Text #4

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.3428. Min Act: -0.1700

Data Index: 482739 (Open Web Text)

Max Activating Token Index: 969

Text #5

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.3399. Min Act: -0.1700

Data Index: 3371421 (Open Web Text)

Max Activating Token Index: 790

Text #6

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.3100. Min Act: -0.1700

Data Index: 7277326 (Open Web Text)

Max Activating Token Index: 411

Text #7

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2942. Min Act: -0.1700

Data Index: 2827633 (Open Web Text)

Max Activating Token Index: 56

Text #8

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2949. Min Act: -0.1700

Data Index: 1438415 (Open Web Text)

Max Activating Token Index: 929

Text #9

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2425. Min Act: -0.1700

Data Index: 3371422 (Open Web Text)

Max Activating Token Index: 104

Text #10

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2729. Min Act: -0.1700

Data Index: 5589463 (Open Web Text)

Max Activating Token Index: 302

Text #11

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2769. Min Act: -0.1700

Data Index: 4379257 (Open Web Text)

Max Activating Token Index: 366

Text #12

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2622. Min Act: -0.1700

Data Index: 975544 (Open Web Text)

Max Activating Token Index: 140

Text #13

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2317. Min Act: -0.1700

Data Index: 109650 (Open Web Text)

Max Activating Token Index: 488

Text #14

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2093. Min Act: -0.1700

Data Index: 1000953 (Open Web Text)

Max Activating Token Index: 179

Text #15

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2389. Min Act: -0.1700

Data Index: 3350893 (Open Web Text)

Max Activating Token Index: 511

Text #16

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2235. Min Act: -0.1700

Data Index: 3219314 (Open Web Text)

Max Activating Token Index: 331

Text #17

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2294. Min Act: -0.1700

Data Index: 6726528 (Open Web Text)

Max Activating Token Index: 601

Text #18

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2264. Min Act: -0.1700

Data Index: 2434788 (Open Web Text)

Max Activating Token Index: 447

Text #19

Max Range: 5.5053. Min Range: -5.5053

Max Act: 5.2218. Min Act: -0.1700

Data Index: 2712103 (Open Web Text)

Max Activating Token Index: 19