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

Dataset: Open Web Text

Neuron 1928 in Layer 3

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: 4.5330. Min Range: -4.5330

Max Act: 4.4942. Min Act: -0.1700

Data Index: 3936441 (Open Web Text)

Max Activating Token Index: 290

Text #1

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.5330. Min Act: -0.1700

Data Index: 8609199 (Open Web Text)

Max Activating Token Index: 292

Text #2

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.5162. Min Act: -0.1700

Data Index: 5265747 (Open Web Text)

Max Activating Token Index: 398

Text #3

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.4936. Min Act: -0.1700

Data Index: 434188 (Open Web Text)

Max Activating Token Index: 1012

Text #4

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.5013. Min Act: -0.1700

Data Index: 6677487 (Open Web Text)

Max Activating Token Index: 722

Text #5

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.4859. Min Act: -0.1700

Data Index: 2087257 (Open Web Text)

Max Activating Token Index: 400

Text #6

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.4510. Min Act: -0.1700

Data Index: 7044750 (Open Web Text)

Max Activating Token Index: 737

Text #7

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.3500. Min Act: -0.1700

Data Index: 2445463 (Open Web Text)

Max Activating Token Index: 998

Text #8

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.4221. Min Act: -0.1700

Data Index: 1579125 (Open Web Text)

Max Activating Token Index: 817

Text #9

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.3799. Min Act: -0.1700

Data Index: 5539165 (Open Web Text)

Max Activating Token Index: 813

Text #10

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.3764. Min Act: -0.1700

Data Index: 3624996 (Open Web Text)

Max Activating Token Index: 725

Text #11

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.3335. Min Act: -0.1700

Data Index: 545289 (Open Web Text)

Max Activating Token Index: 119

Text #12

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.3913. Min Act: -0.1700

Data Index: 7982911 (Open Web Text)

Max Activating Token Index: 631

Text #13

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.3215. Min Act: -0.1700

Data Index: 1193333 (Open Web Text)

Max Activating Token Index: 925

Text #14

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.4230. Min Act: -0.1700

Data Index: 3411519 (Open Web Text)

Max Activating Token Index: 773

Text #15

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.2872. Min Act: -0.1700

Data Index: 3486156 (Open Web Text)

Max Activating Token Index: 619

Text #16

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.2719. Min Act: -0.1700

Data Index: 5904450 (Open Web Text)

Max Activating Token Index: 971

Text #17

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.3040. Min Act: -0.1700

Data Index: 2285763 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.3186. Min Act: -0.1700

Data Index: 8303349 (Open Web Text)

Max Activating Token Index: 532

Text #19

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.2622. Min Act: -0.1700

Data Index: 6801823 (Open Web Text)

Max Activating Token Index: 203