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

Dataset: Open Web Text

Neuron 1975 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: 4.3787. Min Range: -4.3787

Max Act: 4.3787. Min Act: -0.1700

Data Index: 5465713 (Open Web Text)

Max Activating Token Index: 632

Text #1

Max Range: 4.3787. Min Range: -4.3787

Max Act: 4.3366. Min Act: -0.1700

Data Index: 5003601 (Open Web Text)

Max Activating Token Index: 269

Text #2

Max Range: 4.3787. Min Range: -4.3787

Max Act: 4.3226. Min Act: -0.1700

Data Index: 1796126 (Open Web Text)

Max Activating Token Index: 272

Text #3

Max Range: 4.3787. Min Range: -4.3787

Max Act: 4.3279. Min Act: -0.1700

Data Index: 2693854 (Open Web Text)

Max Activating Token Index: 970

Text #4

Max Range: 4.3787. Min Range: -4.3787

Max Act: 4.3297. Min Act: -0.1700

Data Index: 3026148 (Open Web Text)

Max Activating Token Index: 480

Text #5

Max Range: 4.3787. Min Range: -4.3787

Max Act: 4.3520. Min Act: -0.1700

Data Index: 3606354 (Open Web Text)

Max Activating Token Index: 428

Text #6

Max Range: 4.3787. Min Range: -4.3787

Max Act: 4.3528. Min Act: -0.1700

Data Index: 3848064 (Open Web Text)

Max Activating Token Index: 540

Text #7

Max Range: 4.3787. Min Range: -4.3787

Max Act: 4.3367. Min Act: -0.1700

Data Index: 1608906 (Open Web Text)

Max Activating Token Index: 348

Text #8

Max Range: 4.3787. Min Range: -4.3787

Max Act: 4.3126. Min Act: -0.1700

Data Index: 190999 (Open Web Text)

Max Activating Token Index: 89

Text #9

Max Range: 4.3787. Min Range: -4.3787

Max Act: 4.2942. Min Act: -0.1700

Data Index: 4116203 (Open Web Text)

Max Activating Token Index: 553

Text #10

Max Range: 4.3787. Min Range: -4.3787

Max Act: 4.3117. Min Act: -0.1700

Data Index: 1937043 (Open Web Text)

Max Activating Token Index: 645

Text #11

Max Range: 4.3787. Min Range: -4.3787

Max Act: 4.2781. Min Act: -0.1700

Data Index: 8562484 (Open Web Text)

Max Activating Token Index: 101

Text #12

Max Range: 4.3787. Min Range: -4.3787

Max Act: 4.3035. Min Act: -0.1700

Data Index: 7948773 (Open Web Text)

Max Activating Token Index: 492

Text #13

Max Range: 4.3787. Min Range: -4.3787

Max Act: 4.2577. Min Act: -0.1700

Data Index: 3857171 (Open Web Text)

Max Activating Token Index: 887

Text #14

Max Range: 4.3787. Min Range: -4.3787

Max Act: 4.2959. Min Act: -0.1700

Data Index: 1024183 (Open Web Text)

Max Activating Token Index: 200

Text #15

Max Range: 4.3787. Min Range: -4.3787

Max Act: 4.3161. Min Act: -0.1700

Data Index: 5148474 (Open Web Text)

Max Activating Token Index: 436

Text #16

Max Range: 4.3787. Min Range: -4.3787

Max Act: 4.3178. Min Act: -0.1700

Data Index: 2177044 (Open Web Text)

Max Activating Token Index: 426

Text #17

Max Range: 4.3787. Min Range: -4.3787

Max Act: 4.3052. Min Act: -0.1700

Data Index: 4877173 (Open Web Text)

Max Activating Token Index: 535

Text #18

Max Range: 4.3787. Min Range: -4.3787

Max Act: 4.2612. Min Act: -0.1700

Data Index: 305871 (Open Web Text)

Max Activating Token Index: 552

Text #19

Max Range: 4.3787. Min Range: -4.3787

Max Act: 4.2665. Min Act: -0.1700

Data Index: 1200958 (Open Web Text)

Max Activating Token Index: 541