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

Dataset: Open Web Text

Neuron 2990 in Layer 6

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: 4.4829. Min Range: -4.4829

Max Act: 4.4829. Min Act: -0.1700

Data Index: 49867 (Open Web Text)

Max Activating Token Index: 894

Text #1

Max Range: 4.4829. Min Range: -4.4829

Max Act: 4.4065. Min Act: -0.1700

Data Index: 6684962 (Open Web Text)

Max Activating Token Index: 581

Text #2

Max Range: 4.4829. Min Range: -4.4829

Max Act: 4.3242. Min Act: -0.1700

Data Index: 6768044 (Open Web Text)

Max Activating Token Index: 639

Text #3

Max Range: 4.4829. Min Range: -4.4829

Max Act: 4.3461. Min Act: -0.1700

Data Index: 7213259 (Open Web Text)

Max Activating Token Index: 840

Text #4

Max Range: 4.4829. Min Range: -4.4829

Max Act: 4.2972. Min Act: -0.1700

Data Index: 4434169 (Open Web Text)

Max Activating Token Index: 324

Text #5

Max Range: 4.4829. Min Range: -4.4829

Max Act: 4.2597. Min Act: -0.1700

Data Index: 752449 (Open Web Text)

Max Activating Token Index: 237

Text #6

Max Range: 4.4829. Min Range: -4.4829

Max Act: 4.2245. Min Act: -0.1700

Data Index: 1798331 (Open Web Text)

Max Activating Token Index: 664

Text #7

Max Range: 4.4829. Min Range: -4.4829

Max Act: 4.1922. Min Act: -0.1700

Data Index: 8316906 (Open Web Text)

Max Activating Token Index: 705

Text #8

Max Range: 4.4829. Min Range: -4.4829

Max Act: 4.2118. Min Act: -0.1700

Data Index: 6615425 (Open Web Text)

Max Activating Token Index: 58

Text #9

Max Range: 4.4829. Min Range: -4.4829

Max Act: 4.2235. Min Act: -0.1700

Data Index: 5874924 (Open Web Text)

Max Activating Token Index: 81

Text #10

Max Range: 4.4829. Min Range: -4.4829

Max Act: 4.1807. Min Act: -0.1700

Data Index: 1131768 (Open Web Text)

Max Activating Token Index: 609

Text #11

Max Range: 4.4829. Min Range: -4.4829

Max Act: 4.1831. Min Act: -0.1700

Data Index: 3412019 (Open Web Text)

Max Activating Token Index: 468

Text #12

Max Range: 4.4829. Min Range: -4.4829

Max Act: 4.1757. Min Act: -0.1700

Data Index: 4215602 (Open Web Text)

Max Activating Token Index: 28

Text #13

Max Range: 4.4829. Min Range: -4.4829

Max Act: 4.1809. Min Act: -0.1700

Data Index: 5329016 (Open Web Text)

Max Activating Token Index: 812

Text #14

Max Range: 4.4829. Min Range: -4.4829

Max Act: 4.1784. Min Act: -0.1700

Data Index: 8829008 (Open Web Text)

Max Activating Token Index: 90

Text #15

Max Range: 4.4829. Min Range: -4.4829

Max Act: 4.1736. Min Act: -0.1700

Data Index: 2440677 (Open Web Text)

Max Activating Token Index: 420

Text #16

Max Range: 4.4829. Min Range: -4.4829

Max Act: 4.1916. Min Act: -0.1700

Data Index: 2823946 (Open Web Text)

Max Activating Token Index: 691

Text #17

Max Range: 4.4829. Min Range: -4.4829

Max Act: 4.1682. Min Act: -0.1700

Data Index: 423004 (Open Web Text)

Max Activating Token Index: 880

Text #18

Max Range: 4.4829. Min Range: -4.4829

Max Act: 4.1174. Min Act: -0.1700

Data Index: 6661488 (Open Web Text)

Max Activating Token Index: 438

Text #19

Max Range: 4.4829. Min Range: -4.4829

Max Act: 4.1470. Min Act: -0.1700

Data Index: 2457213 (Open Web Text)

Max Activating Token Index: 991