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

Dataset: Open Web Text

Neuron 2555 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: 3.1920. Min Range: -3.1920

Max Act: 3.1920. Min Act: -0.1700

Data Index: 2231050 (Open Web Text)

Max Activating Token Index: 634

Text #1

Max Range: 3.1920. Min Range: -3.1920

Max Act: 3.1651. Min Act: -0.1700

Data Index: 1325015 (Open Web Text)

Max Activating Token Index: 698

Text #2

Max Range: 3.1920. Min Range: -3.1920

Max Act: 3.1387. Min Act: -0.1700

Data Index: 1585465 (Open Web Text)

Max Activating Token Index: 544

Text #3

Max Range: 3.1920. Min Range: -3.1920

Max Act: 3.1237. Min Act: -0.1700

Data Index: 87381 (Open Web Text)

Max Activating Token Index: 392

Text #4

Max Range: 3.1920. Min Range: -3.1920

Max Act: 3.1155. Min Act: -0.1700

Data Index: 5179275 (Open Web Text)

Max Activating Token Index: 362

Text #5

Max Range: 3.1920. Min Range: -3.1920

Max Act: 3.0990. Min Act: -0.1700

Data Index: 6896127 (Open Web Text)

Max Activating Token Index: 866

Text #6

Max Range: 3.1920. Min Range: -3.1920

Max Act: 3.0848. Min Act: -0.1700

Data Index: 6466196 (Open Web Text)

Max Activating Token Index: 616

Text #7

Max Range: 3.1920. Min Range: -3.1920

Max Act: 3.0807. Min Act: -0.1700

Data Index: 4117840 (Open Web Text)

Max Activating Token Index: 458

Text #8

Max Range: 3.1920. Min Range: -3.1920

Max Act: 3.0657. Min Act: -0.1700

Data Index: 397913 (Open Web Text)

Max Activating Token Index: 116

Text #9

Max Range: 3.1920. Min Range: -3.1920

Max Act: 3.0490. Min Act: -0.1700

Data Index: 6453876 (Open Web Text)

Max Activating Token Index: 605

Text #10

Max Range: 3.1920. Min Range: -3.1920

Max Act: 3.0267. Min Act: -0.1700

Data Index: 4876811 (Open Web Text)

Max Activating Token Index: 353

Text #11

Max Range: 3.1920. Min Range: -3.1920

Max Act: 3.0497. Min Act: -0.1700

Data Index: 2390222 (Open Web Text)

Max Activating Token Index: 859

Text #12

Max Range: 3.1920. Min Range: -3.1920

Max Act: 3.0290. Min Act: -0.1700

Data Index: 3960636 (Open Web Text)

Max Activating Token Index: 422

Text #13

Max Range: 3.1920. Min Range: -3.1920

Max Act: 3.0661. Min Act: -0.1700

Data Index: 2772442 (Open Web Text)

Max Activating Token Index: 707

Text #14

Max Range: 3.1920. Min Range: -3.1920

Max Act: 3.0560. Min Act: -0.1700

Data Index: 6691685 (Open Web Text)

Max Activating Token Index: 361

Text #15

Max Range: 3.1920. Min Range: -3.1920

Max Act: 3.0223. Min Act: -0.1700

Data Index: 2682050 (Open Web Text)

Max Activating Token Index: 763

Text #16

Max Range: 3.1920. Min Range: -3.1920

Max Act: 3.0500. Min Act: -0.1700

Data Index: 5375631 (Open Web Text)

Max Activating Token Index: 834

Text #17

Max Range: 3.1920. Min Range: -3.1920

Max Act: 3.0097. Min Act: -0.1700

Data Index: 5580036 (Open Web Text)

Max Activating Token Index: 304

Text #18

Max Range: 3.1920. Min Range: -3.1920

Max Act: 3.0251. Min Act: -0.1700

Data Index: 2946646 (Open Web Text)

Max Activating Token Index: 390

Text #19

Max Range: 3.1920. Min Range: -3.1920

Max Act: 3.0181. Min Act: -0.1700

Data Index: 3969600 (Open Web Text)

Max Activating Token Index: 504