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

Dataset: Open Web Text

Neuron 140 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: 4.0312. Min Range: -4.0312

Max Act: 4.0312. Min Act: -0.1700

Data Index: 2105613 (Open Web Text)

Max Activating Token Index: 975

Text #1

Max Range: 4.0312. Min Range: -4.0312

Max Act: 4.0288. Min Act: -0.1700

Data Index: 2937336 (Open Web Text)

Max Activating Token Index: 607

Text #2

Max Range: 4.0312. Min Range: -4.0312

Max Act: 3.9901. Min Act: -0.1700

Data Index: 2882728 (Open Web Text)

Max Activating Token Index: 256

Text #3

Max Range: 4.0312. Min Range: -4.0312

Max Act: 3.9532. Min Act: -0.1700

Data Index: 4391411 (Open Web Text)

Max Activating Token Index: 196

Text #4

Max Range: 4.0312. Min Range: -4.0312

Max Act: 3.9578. Min Act: -0.1700

Data Index: 5944194 (Open Web Text)

Max Activating Token Index: 712

Text #5

Max Range: 4.0312. Min Range: -4.0312

Max Act: 3.9278. Min Act: -0.1700

Data Index: 2804639 (Open Web Text)

Max Activating Token Index: 221

Text #6

Max Range: 4.0312. Min Range: -4.0312

Max Act: 3.8457. Min Act: -0.1700

Data Index: 6477025 (Open Web Text)

Max Activating Token Index: 237

Text #7

Max Range: 4.0312. Min Range: -4.0312

Max Act: 3.8727. Min Act: -0.1700

Data Index: 8159426 (Open Web Text)

Max Activating Token Index: 324

Text #8

Max Range: 4.0312. Min Range: -4.0312

Max Act: 3.8738. Min Act: -0.1700

Data Index: 596317 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.0312. Min Range: -4.0312

Max Act: 3.8176. Min Act: -0.1700

Data Index: 4528546 (Open Web Text)

Max Activating Token Index: 560

Text #10

Max Range: 4.0312. Min Range: -4.0312

Max Act: 3.8192. Min Act: -0.1700

Data Index: 3078513 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 4.0312. Min Range: -4.0312

Max Act: 3.7720. Min Act: -0.1700

Data Index: 6916557 (Open Web Text)

Max Activating Token Index: 738

Text #12

Max Range: 4.0312. Min Range: -4.0312

Max Act: 3.7674. Min Act: -0.1700

Data Index: 2767968 (Open Web Text)

Max Activating Token Index: 906

Text #13

Max Range: 4.0312. Min Range: -4.0312

Max Act: 3.7953. Min Act: -0.1700

Data Index: 8261453 (Open Web Text)

Max Activating Token Index: 366

Text #14

Max Range: 4.0312. Min Range: -4.0312

Max Act: 3.7795. Min Act: -0.1700

Data Index: 1591289 (Open Web Text)

Max Activating Token Index: 1008

Text #15

Max Range: 4.0312. Min Range: -4.0312

Max Act: 3.7509. Min Act: -0.1700

Data Index: 2922649 (Open Web Text)

Max Activating Token Index: 435

Text #16

Max Range: 4.0312. Min Range: -4.0312

Max Act: 3.7781. Min Act: -0.1700

Data Index: 1433074 (Open Web Text)

Max Activating Token Index: 139

Text #17

Max Range: 4.0312. Min Range: -4.0312

Max Act: 3.7324. Min Act: -0.1700

Data Index: 1847497 (Open Web Text)

Max Activating Token Index: 871

Text #18

Max Range: 4.0312. Min Range: -4.0312

Max Act: 3.7613. Min Act: -0.1700

Data Index: 5999183 (Open Web Text)

Max Activating Token Index: 188

Text #19

Max Range: 4.0312. Min Range: -4.0312

Max Act: 3.7332. Min Act: -0.1700

Data Index: 6097790 (Open Web Text)

Max Activating Token Index: 864