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

Dataset: Open Web Text

Neuron 726 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: 3.3516. Min Range: -3.3516

Max Act: 3.3516. Min Act: -0.1700

Data Index: 4232583 (Open Web Text)

Max Activating Token Index: 237

Text #1

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.3076. Min Act: -0.1700

Data Index: 2407924 (Open Web Text)

Max Activating Token Index: 287

Text #2

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.2927. Min Act: -0.1700

Data Index: 2397424 (Open Web Text)

Max Activating Token Index: 132

Text #3

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.3018. Min Act: -0.1700

Data Index: 1025709 (Open Web Text)

Max Activating Token Index: 600

Text #4

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.3004. Min Act: -0.1700

Data Index: 4132801 (Open Web Text)

Max Activating Token Index: 790

Text #5

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.2683. Min Act: -0.1700

Data Index: 3254837 (Open Web Text)

Max Activating Token Index: 365

Text #6

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.2659. Min Act: -0.1700

Data Index: 2051870 (Open Web Text)

Max Activating Token Index: 51

Text #7

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.2544. Min Act: -0.1700

Data Index: 6577253 (Open Web Text)

Max Activating Token Index: 454

Text #8

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.2514. Min Act: -0.1700

Data Index: 6996420 (Open Web Text)

Max Activating Token Index: 212

Text #9

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.2511. Min Act: -0.1700

Data Index: 3445343 (Open Web Text)

Max Activating Token Index: 512

Text #10

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.2314. Min Act: -0.1700

Data Index: 3513775 (Open Web Text)

Max Activating Token Index: 46

Text #11

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.2340. Min Act: -0.1700

Data Index: 4213118 (Open Web Text)

Max Activating Token Index: 516

Text #12

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.2098. Min Act: -0.1700

Data Index: 5016805 (Open Web Text)

Max Activating Token Index: 550

Text #13

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.2245. Min Act: -0.1700

Data Index: 4139448 (Open Web Text)

Max Activating Token Index: 807

Text #14

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.2290. Min Act: -0.1700

Data Index: 3070691 (Open Web Text)

Max Activating Token Index: 244

Text #15

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.2308. Min Act: -0.1700

Data Index: 3110668 (Open Web Text)

Max Activating Token Index: 72

Text #16

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.2086. Min Act: -0.1700

Data Index: 8309404 (Open Web Text)

Max Activating Token Index: 206

Text #17

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.2159. Min Act: -0.1700

Data Index: 5266016 (Open Web Text)

Max Activating Token Index: 528

Text #18

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.2205. Min Act: -0.1700

Data Index: 1397571 (Open Web Text)

Max Activating Token Index: 436

Text #19

Max Range: 3.3516. Min Range: -3.3516

Max Act: 3.2306. Min Act: -0.1700

Data Index: 7944035 (Open Web Text)

Max Activating Token Index: 958