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

Dataset: Open Web Text

Neuron 1404 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: 4.7312. Min Range: -4.7312

Max Act: 4.7312. Min Act: -0.1700

Data Index: 7306893 (Open Web Text)

Max Activating Token Index: 378

Text #1

Max Range: 4.7312. Min Range: -4.7312

Max Act: 4.6908. Min Act: -0.1700

Data Index: 5753665 (Open Web Text)

Max Activating Token Index: 603

Text #2

Max Range: 4.7312. Min Range: -4.7312

Max Act: 4.6706. Min Act: -0.1700

Data Index: 5328546 (Open Web Text)

Max Activating Token Index: 22

Text #3

Max Range: 4.7312. Min Range: -4.7312

Max Act: 4.6587. Min Act: -0.1700

Data Index: 6335478 (Open Web Text)

Max Activating Token Index: 901

Text #4

Max Range: 4.7312. Min Range: -4.7312

Max Act: 4.6791. Min Act: -0.1700

Data Index: 182793 (Open Web Text)

Max Activating Token Index: 742

Text #5

Max Range: 4.7312. Min Range: -4.7312

Max Act: 4.6585. Min Act: -0.1700

Data Index: 8476582 (Open Web Text)

Max Activating Token Index: 312

Text #6

Max Range: 4.7312. Min Range: -4.7312

Max Act: 4.6399. Min Act: -0.1700

Data Index: 1237998 (Open Web Text)

Max Activating Token Index: 896

Text #7

Max Range: 4.7312. Min Range: -4.7312

Max Act: 4.6506. Min Act: -0.1700

Data Index: 1152196 (Open Web Text)

Max Activating Token Index: 77

Text #8

Max Range: 4.7312. Min Range: -4.7312

Max Act: 4.6530. Min Act: -0.1700

Data Index: 6062790 (Open Web Text)

Max Activating Token Index: 891

Text #9

Max Range: 4.7312. Min Range: -4.7312

Max Act: 4.5932. Min Act: -0.1700

Data Index: 7308552 (Open Web Text)

Max Activating Token Index: 856

Text #10

Max Range: 4.7312. Min Range: -4.7312

Max Act: 4.6271. Min Act: -0.1700

Data Index: 8004453 (Open Web Text)

Max Activating Token Index: 356

Text #11

Max Range: 4.7312. Min Range: -4.7312

Max Act: 4.6250. Min Act: -0.1700

Data Index: 1613215 (Open Web Text)

Max Activating Token Index: 476

Text #12

Max Range: 4.7312. Min Range: -4.7312

Max Act: 4.5795. Min Act: -0.1700

Data Index: 1561067 (Open Web Text)

Max Activating Token Index: 912

Text #13

Max Range: 4.7312. Min Range: -4.7312

Max Act: 4.5670. Min Act: -0.1700

Data Index: 7158206 (Open Web Text)

Max Activating Token Index: 76

Text #14

Max Range: 4.7312. Min Range: -4.7312

Max Act: 4.5870. Min Act: -0.1700

Data Index: 435105 (Open Web Text)

Max Activating Token Index: 886

Text #15

Max Range: 4.7312. Min Range: -4.7312

Max Act: 4.5586. Min Act: -0.1700

Data Index: 5637887 (Open Web Text)

Max Activating Token Index: 441

Text #16

Max Range: 4.7312. Min Range: -4.7312

Max Act: 4.5649. Min Act: -0.1700

Data Index: 5047938 (Open Web Text)

Max Activating Token Index: 986

Text #17

Max Range: 4.7312. Min Range: -4.7312

Max Act: 4.5486. Min Act: -0.1700

Data Index: 4183596 (Open Web Text)

Max Activating Token Index: 551

Text #18

Max Range: 4.7312. Min Range: -4.7312

Max Act: 4.5551. Min Act: -0.1700

Data Index: 7555061 (Open Web Text)

Max Activating Token Index: 814

Text #19

Max Range: 4.7312. Min Range: -4.7312

Max Act: 4.5566. Min Act: -0.1700

Data Index: 5436980 (Open Web Text)

Max Activating Token Index: 603