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

Dataset: Open Web Text

Neuron 895 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: 4.5530. Min Range: -4.5530

Max Act: 4.5530. Min Act: -0.1700

Data Index: 8501709 (Open Web Text)

Max Activating Token Index: 1011

Text #1

Max Range: 4.5530. Min Range: -4.5530

Max Act: 4.4585. Min Act: -0.1700

Data Index: 5652379 (Open Web Text)

Max Activating Token Index: 643

Text #2

Max Range: 4.5530. Min Range: -4.5530

Max Act: 4.4479. Min Act: -0.1700

Data Index: 6761307 (Open Web Text)

Max Activating Token Index: 672

Text #3

Max Range: 4.5530. Min Range: -4.5530

Max Act: 4.4260. Min Act: -0.1700

Data Index: 5703981 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 4.5530. Min Range: -4.5530

Max Act: 4.4175. Min Act: -0.1700

Data Index: 426869 (Open Web Text)

Max Activating Token Index: 1012

Text #5

Max Range: 4.5530. Min Range: -4.5530

Max Act: 4.3879. Min Act: -0.1700

Data Index: 8184152 (Open Web Text)

Max Activating Token Index: 691

Text #6

Max Range: 4.5530. Min Range: -4.5530

Max Act: 4.3302. Min Act: -0.1700

Data Index: 6812193 (Open Web Text)

Max Activating Token Index: 920

Text #7

Max Range: 4.5530. Min Range: -4.5530

Max Act: 4.3378. Min Act: -0.1700

Data Index: 2649667 (Open Web Text)

Max Activating Token Index: 959

Text #8

Max Range: 4.5530. Min Range: -4.5530

Max Act: 4.3235. Min Act: -0.1700

Data Index: 500433 (Open Web Text)

Max Activating Token Index: 651

Text #9

Max Range: 4.5530. Min Range: -4.5530

Max Act: 4.3360. Min Act: -0.1700

Data Index: 6854038 (Open Web Text)

Max Activating Token Index: 930

Text #10

Max Range: 4.5530. Min Range: -4.5530

Max Act: 4.3584. Min Act: -0.1700

Data Index: 2371032 (Open Web Text)

Max Activating Token Index: 583

Text #11

Max Range: 4.5530. Min Range: -4.5530

Max Act: 4.3402. Min Act: -0.1700

Data Index: 6818893 (Open Web Text)

Max Activating Token Index: 1018

Text #12

Max Range: 4.5530. Min Range: -4.5530

Max Act: 4.3592. Min Act: -0.1700

Data Index: 7279409 (Open Web Text)

Max Activating Token Index: 480

Text #13

Max Range: 4.5530. Min Range: -4.5530

Max Act: 4.3563. Min Act: -0.1700

Data Index: 872303 (Open Web Text)

Max Activating Token Index: 487

Text #14

Max Range: 4.5530. Min Range: -4.5530

Max Act: 4.3536. Min Act: -0.1700

Data Index: 4063324 (Open Web Text)

Max Activating Token Index: 1022

Text #15

Max Range: 4.5530. Min Range: -4.5530

Max Act: 4.3103. Min Act: -0.1700

Data Index: 6789588 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 4.5530. Min Range: -4.5530

Max Act: 4.3044. Min Act: -0.1700

Data Index: 5223753 (Open Web Text)

Max Activating Token Index: 15

Text #17

Max Range: 4.5530. Min Range: -4.5530

Max Act: 4.3253. Min Act: -0.1700

Data Index: 2696984 (Open Web Text)

Max Activating Token Index: 602

Text #18

Max Range: 4.5530. Min Range: -4.5530

Max Act: 4.3038. Min Act: -0.1700

Data Index: 2728668 (Open Web Text)

Max Activating Token Index: 764

Text #19

Max Range: 4.5530. Min Range: -4.5530

Max Act: 4.3177. Min Act: -0.1700

Data Index: 54905 (Open Web Text)

Max Activating Token Index: 238