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

Dataset: Open Web Text

Neuron 2345 in Layer 2

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: 3.0565. Min Range: -3.0565

Max Act: 3.0565. Min Act: -0.1700

Data Index: 2799621 (Open Web Text)

Max Activating Token Index: 862

Text #1

Max Range: 3.0565. Min Range: -3.0565

Max Act: 2.9506. Min Act: -0.1700

Data Index: 4800488 (Open Web Text)

Max Activating Token Index: 620

Text #2

Max Range: 3.0565. Min Range: -3.0565

Max Act: 2.9462. Min Act: -0.1700

Data Index: 2148319 (Open Web Text)

Max Activating Token Index: 602

Text #3

Max Range: 3.0565. Min Range: -3.0565

Max Act: 2.9209. Min Act: -0.1700

Data Index: 199037 (Open Web Text)

Max Activating Token Index: 965

Text #4

Max Range: 3.0565. Min Range: -3.0565

Max Act: 2.8732. Min Act: -0.1700

Data Index: 3351191 (Open Web Text)

Max Activating Token Index: 449

Text #5

Max Range: 3.0565. Min Range: -3.0565

Max Act: 2.9012. Min Act: -0.1700

Data Index: 7383545 (Open Web Text)

Max Activating Token Index: 299

Text #6

Max Range: 3.0565. Min Range: -3.0565

Max Act: 2.8886. Min Act: -0.1700

Data Index: 5857056 (Open Web Text)

Max Activating Token Index: 758

Text #7

Max Range: 3.0565. Min Range: -3.0565

Max Act: 2.8728. Min Act: -0.1700

Data Index: 774736 (Open Web Text)

Max Activating Token Index: 144

Text #8

Max Range: 3.0565. Min Range: -3.0565

Max Act: 2.8811. Min Act: -0.1700

Data Index: 69612 (Open Web Text)

Max Activating Token Index: 76

Text #9

Max Range: 3.0565. Min Range: -3.0565

Max Act: 2.8682. Min Act: -0.1700

Data Index: 3924916 (Open Web Text)

Max Activating Token Index: 479

Text #10

Max Range: 3.0565. Min Range: -3.0565

Max Act: 2.8784. Min Act: -0.1700

Data Index: 3136937 (Open Web Text)

Max Activating Token Index: 738

Text #11

Max Range: 3.0565. Min Range: -3.0565

Max Act: 2.8547. Min Act: -0.1700

Data Index: 199032 (Open Web Text)

Max Activating Token Index: 183

Text #12

Max Range: 3.0565. Min Range: -3.0565

Max Act: 2.8571. Min Act: -0.1700

Data Index: 5626054 (Open Web Text)

Max Activating Token Index: 163

Text #13

Max Range: 3.0565. Min Range: -3.0565

Max Act: 2.8711. Min Act: -0.1700

Data Index: 6597502 (Open Web Text)

Max Activating Token Index: 639

Text #14

Max Range: 3.0565. Min Range: -3.0565

Max Act: 2.8439. Min Act: -0.1700

Data Index: 2995191 (Open Web Text)

Max Activating Token Index: 550

Text #15

Max Range: 3.0565. Min Range: -3.0565

Max Act: 2.8249. Min Act: -0.1700

Data Index: 679664 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.0565. Min Range: -3.0565

Max Act: 2.8294. Min Act: -0.1700

Data Index: 7747190 (Open Web Text)

Max Activating Token Index: 109

Text #17

Max Range: 3.0565. Min Range: -3.0565

Max Act: 2.8060. Min Act: -0.1700

Data Index: 2204937 (Open Web Text)

Max Activating Token Index: 125

Text #18

Max Range: 3.0565. Min Range: -3.0565

Max Act: 2.8175. Min Act: -0.1700

Data Index: 7210367 (Open Web Text)

Max Activating Token Index: 66

Text #19

Max Range: 3.0565. Min Range: -3.0565

Max Act: 2.8123. Min Act: -0.1700

Data Index: 4974460 (Open Web Text)

Max Activating Token Index: 22