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

Dataset: Open Web Text

Neuron 689 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: 4.5862. Min Range: -4.5862

Max Act: 4.5862. Min Act: -0.1700

Data Index: 1632537 (Open Web Text)

Max Activating Token Index: 108

Text #1

Max Range: 4.5862. Min Range: -4.5862

Max Act: 4.5558. Min Act: -0.1700

Data Index: 7836825 (Open Web Text)

Max Activating Token Index: 560

Text #2

Max Range: 4.5862. Min Range: -4.5862

Max Act: 4.4935. Min Act: -0.1700

Data Index: 6857479 (Open Web Text)

Max Activating Token Index: 630

Text #3

Max Range: 4.5862. Min Range: -4.5862

Max Act: 4.4438. Min Act: -0.1700

Data Index: 3280448 (Open Web Text)

Max Activating Token Index: 547

Text #4

Max Range: 4.5862. Min Range: -4.5862

Max Act: 4.4076. Min Act: -0.1700

Data Index: 506545 (Open Web Text)

Max Activating Token Index: 852

Text #5

Max Range: 4.5862. Min Range: -4.5862

Max Act: 4.3313. Min Act: -0.1700

Data Index: 4535903 (Open Web Text)

Max Activating Token Index: 187

Text #6

Max Range: 4.5862. Min Range: -4.5862

Max Act: 4.3387. Min Act: -0.1700

Data Index: 7789810 (Open Web Text)

Max Activating Token Index: 171

Text #7

Max Range: 4.5862. Min Range: -4.5862

Max Act: 4.3044. Min Act: -0.1700

Data Index: 1122854 (Open Web Text)

Max Activating Token Index: 409

Text #8

Max Range: 4.5862. Min Range: -4.5862

Max Act: 4.3070. Min Act: -0.1700

Data Index: 1970772 (Open Web Text)

Max Activating Token Index: 282

Text #9

Max Range: 4.5862. Min Range: -4.5862

Max Act: 4.3147. Min Act: -0.1700

Data Index: 2000824 (Open Web Text)

Max Activating Token Index: 999

Text #10

Max Range: 4.5862. Min Range: -4.5862

Max Act: 4.3484. Min Act: -0.1700

Data Index: 3431178 (Open Web Text)

Max Activating Token Index: 454

Text #11

Max Range: 4.5862. Min Range: -4.5862

Max Act: 4.2855. Min Act: -0.1700

Data Index: 1390795 (Open Web Text)

Max Activating Token Index: 299

Text #12

Max Range: 4.5862. Min Range: -4.5862

Max Act: 4.2549. Min Act: -0.1700

Data Index: 562118 (Open Web Text)

Max Activating Token Index: 147

Text #13

Max Range: 4.5862. Min Range: -4.5862

Max Act: 4.2541. Min Act: -0.1700

Data Index: 5996313 (Open Web Text)

Max Activating Token Index: 266

Text #14

Max Range: 4.5862. Min Range: -4.5862

Max Act: 4.3052. Min Act: -0.1700

Data Index: 5792890 (Open Web Text)

Max Activating Token Index: 1014

Text #15

Max Range: 4.5862. Min Range: -4.5862

Max Act: 4.2701. Min Act: -0.1700

Data Index: 1702051 (Open Web Text)

Max Activating Token Index: 140

Text #16

Max Range: 4.5862. Min Range: -4.5862

Max Act: 4.3083. Min Act: -0.1700

Data Index: 160127 (Open Web Text)

Max Activating Token Index: 426

Text #17

Max Range: 4.5862. Min Range: -4.5862

Max Act: 4.2781. Min Act: -0.1700

Data Index: 1809053 (Open Web Text)

Max Activating Token Index: 356

Text #18

Max Range: 4.5862. Min Range: -4.5862

Max Act: 4.2502. Min Act: -0.1700

Data Index: 6205182 (Open Web Text)

Max Activating Token Index: 310

Text #19

Max Range: 4.5862. Min Range: -4.5862

Max Act: 4.2306. Min Act: -0.1700

Data Index: 6956516 (Open Web Text)

Max Activating Token Index: 164