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

Dataset: Open Web Text

Neuron 2309 in Layer 4

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: 3.3195. Min Range: -3.3195

Max Act: 3.3195. Min Act: -0.1700

Data Index: 1121311 (Open Web Text)

Max Activating Token Index: 261

Text #1

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2886. Min Act: -0.1700

Data Index: 3098138 (Open Web Text)

Max Activating Token Index: 646

Text #2

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2490. Min Act: -0.1700

Data Index: 1774585 (Open Web Text)

Max Activating Token Index: 954

Text #3

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2435. Min Act: -0.1700

Data Index: 7535177 (Open Web Text)

Max Activating Token Index: 619

Text #4

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2422. Min Act: -0.1700

Data Index: 6775490 (Open Web Text)

Max Activating Token Index: 193

Text #5

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2441. Min Act: -0.1700

Data Index: 288529 (Open Web Text)

Max Activating Token Index: 97

Text #6

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2273. Min Act: -0.1700

Data Index: 3219267 (Open Web Text)

Max Activating Token Index: 600

Text #7

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2352. Min Act: -0.1700

Data Index: 5812423 (Open Web Text)

Max Activating Token Index: 738

Text #8

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2208. Min Act: -0.1700

Data Index: 3243735 (Open Web Text)

Max Activating Token Index: 532

Text #9

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2341. Min Act: -0.1700

Data Index: 2359695 (Open Web Text)

Max Activating Token Index: 149

Text #10

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2086. Min Act: -0.1700

Data Index: 8255935 (Open Web Text)

Max Activating Token Index: 467

Text #11

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2126. Min Act: -0.1700

Data Index: 3077034 (Open Web Text)

Max Activating Token Index: 179

Text #12

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2211. Min Act: -0.1700

Data Index: 5208638 (Open Web Text)

Max Activating Token Index: 680

Text #13

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2066. Min Act: -0.1700

Data Index: 556708 (Open Web Text)

Max Activating Token Index: 522

Text #14

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.1994. Min Act: -0.1700

Data Index: 134579 (Open Web Text)

Max Activating Token Index: 219

Text #15

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2054. Min Act: -0.1700

Data Index: 3372366 (Open Web Text)

Max Activating Token Index: 43

Text #16

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.1942. Min Act: -0.1700

Data Index: 5374925 (Open Web Text)

Max Activating Token Index: 20

Text #17

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2045. Min Act: -0.1700

Data Index: 2271867 (Open Web Text)

Max Activating Token Index: 487

Text #18

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.1892. Min Act: -0.1700

Data Index: 4947845 (Open Web Text)

Max Activating Token Index: 670

Text #19

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.1968. Min Act: -0.1700

Data Index: 2985341 (Open Web Text)

Max Activating Token Index: 631