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

Dataset: Open Web Text

Neuron 336 in Layer 2

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: 4.5358. Min Range: -4.5358

Max Act: 4.5271. Min Act: -0.1700

Data Index: 5108140 (Open Web Text)

Max Activating Token Index: 122

Text #1

Max Range: 4.5358. Min Range: -4.5358

Max Act: 4.5358. Min Act: -0.1700

Data Index: 1624365 (Open Web Text)

Max Activating Token Index: 287

Text #2

Max Range: 4.5358. Min Range: -4.5358

Max Act: 4.3445. Min Act: -0.1700

Data Index: 3088185 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 4.5358. Min Range: -4.5358

Max Act: 4.3278. Min Act: -0.1700

Data Index: 8733759 (Open Web Text)

Max Activating Token Index: 367

Text #4

Max Range: 4.5358. Min Range: -4.5358

Max Act: 4.3565. Min Act: -0.1700

Data Index: 6142005 (Open Web Text)

Max Activating Token Index: 18

Text #5

Max Range: 4.5358. Min Range: -4.5358

Max Act: 4.3533. Min Act: -0.1700

Data Index: 5108159 (Open Web Text)

Max Activating Token Index: 800

Text #6

Max Range: 4.5358. Min Range: -4.5358

Max Act: 4.3564. Min Act: -0.1700

Data Index: 5466337 (Open Web Text)

Max Activating Token Index: 202

Text #7

Max Range: 4.5358. Min Range: -4.5358

Max Act: 4.3069. Min Act: -0.1700

Data Index: 3405483 (Open Web Text)

Max Activating Token Index: 1010

Text #8

Max Range: 4.5358. Min Range: -4.5358

Max Act: 4.3345. Min Act: -0.1700

Data Index: 7549254 (Open Web Text)

Max Activating Token Index: 740

Text #9

Max Range: 4.5358. Min Range: -4.5358

Max Act: 4.3139. Min Act: -0.1700

Data Index: 7515683 (Open Web Text)

Max Activating Token Index: 671

Text #10

Max Range: 4.5358. Min Range: -4.5358

Max Act: 4.3232. Min Act: -0.1700

Data Index: 6244192 (Open Web Text)

Max Activating Token Index: 309

Text #11

Max Range: 4.5358. Min Range: -4.5358

Max Act: 4.3107. Min Act: -0.1700

Data Index: 2679527 (Open Web Text)

Max Activating Token Index: 818

Text #12

Max Range: 4.5358. Min Range: -4.5358

Max Act: 4.2901. Min Act: -0.1700

Data Index: 2553044 (Open Web Text)

Max Activating Token Index: 209

Text #13

Max Range: 4.5358. Min Range: -4.5358

Max Act: 4.3091. Min Act: -0.1700

Data Index: 8544420 (Open Web Text)

Max Activating Token Index: 198

Text #14

Max Range: 4.5358. Min Range: -4.5358

Max Act: 4.2963. Min Act: -0.1700

Data Index: 4217791 (Open Web Text)

Max Activating Token Index: 331

Text #15

Max Range: 4.5358. Min Range: -4.5358

Max Act: 4.2763. Min Act: -0.1700

Data Index: 5281317 (Open Web Text)

Max Activating Token Index: 596

Text #16

Max Range: 4.5358. Min Range: -4.5358

Max Act: 4.3053. Min Act: -0.1700

Data Index: 5226678 (Open Web Text)

Max Activating Token Index: 73

Text #17

Max Range: 4.5358. Min Range: -4.5358

Max Act: 4.3007. Min Act: -0.1700

Data Index: 4351007 (Open Web Text)

Max Activating Token Index: 67

Text #18

Max Range: 4.5358. Min Range: -4.5358

Max Act: 4.2964. Min Act: -0.1700

Data Index: 2658605 (Open Web Text)

Max Activating Token Index: 20

Text #19

Max Range: 4.5358. Min Range: -4.5358

Max Act: 4.2753. Min Act: -0.1700

Data Index: 7348617 (Open Web Text)

Max Activating Token Index: 617