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

Dataset: Open Web Text

Neuron 3021 in Layer 0

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: 3.8408. Min Range: -3.8408

Max Act: 3.8408. Min Act: -0.1700

Data Index: 7733504 (Open Web Text)

Max Activating Token Index: 57

Text #1

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.7734. Min Act: -0.1700

Data Index: 537607 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.7508. Min Act: -0.1700

Data Index: 918435 (Open Web Text)

Max Activating Token Index: 487

Text #3

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.7175. Min Act: -0.1700

Data Index: 8798898 (Open Web Text)

Max Activating Token Index: 26

Text #4

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.7142. Min Act: -0.1700

Data Index: 6104936 (Open Web Text)

Max Activating Token Index: 190

Text #5

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.6976. Min Act: -0.1700

Data Index: 4693018 (Open Web Text)

Max Activating Token Index: 299

Text #6

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.6848. Min Act: -0.1700

Data Index: 3883051 (Open Web Text)

Max Activating Token Index: 855

Text #7

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.6489. Min Act: -0.1700

Data Index: 503245 (Open Web Text)

Max Activating Token Index: 389

Text #8

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.6477. Min Act: -0.1700

Data Index: 3009942 (Open Web Text)

Max Activating Token Index: 631

Text #9

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.6293. Min Act: -0.1700

Data Index: 469550 (Open Web Text)

Max Activating Token Index: 998

Text #10

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.6390. Min Act: -0.1700

Data Index: 1868376 (Open Web Text)

Max Activating Token Index: 680

Text #11

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.6331. Min Act: -0.1700

Data Index: 6853520 (Open Web Text)

Max Activating Token Index: 77

Text #12

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.5912. Min Act: -0.1700

Data Index: 747031 (Open Web Text)

Max Activating Token Index: 831

Text #13

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.6030. Min Act: -0.1700

Data Index: 2193511 (Open Web Text)

Max Activating Token Index: 458

Text #14

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.6046. Min Act: -0.1700

Data Index: 5827348 (Open Web Text)

Max Activating Token Index: 107

Text #15

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.5965. Min Act: -0.1700

Data Index: 6142643 (Open Web Text)

Max Activating Token Index: 604

Text #16

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.5907. Min Act: -0.1700

Data Index: 6361368 (Open Web Text)

Max Activating Token Index: 697

Text #17

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.5882. Min Act: -0.1700

Data Index: 6560632 (Open Web Text)

Max Activating Token Index: 324

Text #18

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.5853. Min Act: -0.1700

Data Index: 6586716 (Open Web Text)

Max Activating Token Index: 100

Text #19

Max Range: 3.8408. Min Range: -3.8408

Max Act: 3.6099. Min Act: -0.1700

Data Index: 7799443 (Open Web Text)

Max Activating Token Index: 952