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

Dataset: Open Web Text

Neuron 540 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: 3.8102. Min Range: -3.8102

Max Act: 3.8102. Min Act: -0.1700

Data Index: 5400206 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.8102. Min Range: -3.8102

Max Act: 3.6806. Min Act: -0.1700

Data Index: 1589110 (Open Web Text)

Max Activating Token Index: 724

Text #2

Max Range: 3.8102. Min Range: -3.8102

Max Act: 3.7003. Min Act: -0.1700

Data Index: 2291054 (Open Web Text)

Max Activating Token Index: 955

Text #3

Max Range: 3.8102. Min Range: -3.8102

Max Act: 3.6822. Min Act: -0.1700

Data Index: 8643852 (Open Web Text)

Max Activating Token Index: 489

Text #4

Max Range: 3.8102. Min Range: -3.8102

Max Act: 3.6844. Min Act: -0.1700

Data Index: 8319835 (Open Web Text)

Max Activating Token Index: 609

Text #5

Max Range: 3.8102. Min Range: -3.8102

Max Act: 3.6568. Min Act: -0.1700

Data Index: 7443895 (Open Web Text)

Max Activating Token Index: 617

Text #6

Max Range: 3.8102. Min Range: -3.8102

Max Act: 3.6323. Min Act: -0.1700

Data Index: 4593089 (Open Web Text)

Max Activating Token Index: 785

Text #7

Max Range: 3.8102. Min Range: -3.8102

Max Act: 3.6389. Min Act: -0.1700

Data Index: 511717 (Open Web Text)

Max Activating Token Index: 591

Text #8

Max Range: 3.8102. Min Range: -3.8102

Max Act: 3.6191. Min Act: -0.1700

Data Index: 5383695 (Open Web Text)

Max Activating Token Index: 941

Text #9

Max Range: 3.8102. Min Range: -3.8102

Max Act: 3.6497. Min Act: -0.1700

Data Index: 1314607 (Open Web Text)

Max Activating Token Index: 871

Text #10

Max Range: 3.8102. Min Range: -3.8102

Max Act: 3.6311. Min Act: -0.1700

Data Index: 5261331 (Open Web Text)

Max Activating Token Index: 126

Text #11

Max Range: 3.8102. Min Range: -3.8102

Max Act: 3.6123. Min Act: -0.1700

Data Index: 8757790 (Open Web Text)

Max Activating Token Index: 70

Text #12

Max Range: 3.8102. Min Range: -3.8102

Max Act: 3.6298. Min Act: -0.1700

Data Index: 6400350 (Open Web Text)

Max Activating Token Index: 1008

Text #13

Max Range: 3.8102. Min Range: -3.8102

Max Act: 3.6493. Min Act: -0.1700

Data Index: 6278374 (Open Web Text)

Max Activating Token Index: 512

Text #14

Max Range: 3.8102. Min Range: -3.8102

Max Act: 3.6334. Min Act: -0.1700

Data Index: 4391751 (Open Web Text)

Max Activating Token Index: 1021

Text #15

Max Range: 3.8102. Min Range: -3.8102

Max Act: 3.6236. Min Act: -0.1700

Data Index: 2276034 (Open Web Text)

Max Activating Token Index: 17

Text #16

Max Range: 3.8102. Min Range: -3.8102

Max Act: 3.6408. Min Act: -0.1700

Data Index: 901763 (Open Web Text)

Max Activating Token Index: 998

Text #17

Max Range: 3.8102. Min Range: -3.8102

Max Act: 3.6325. Min Act: -0.1700

Data Index: 8235894 (Open Web Text)

Max Activating Token Index: 75

Text #18

Max Range: 3.8102. Min Range: -3.8102

Max Act: 3.6282. Min Act: -0.1700

Data Index: 5526020 (Open Web Text)

Max Activating Token Index: 977

Text #19

Max Range: 3.8102. Min Range: -3.8102

Max Act: 3.5931. Min Act: -0.1700

Data Index: 1824172 (Open Web Text)

Max Activating Token Index: 519