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

Dataset: Open Web Text

Neuron 2952 in Layer 4

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: 3.7809. Min Range: -3.7809

Max Act: 3.7809. Min Act: -0.1700

Data Index: 318598 (Open Web Text)

Max Activating Token Index: 765

Text #1

Max Range: 3.7809. Min Range: -3.7809

Max Act: 3.7663. Min Act: -0.1700

Data Index: 7700456 (Open Web Text)

Max Activating Token Index: 750

Text #2

Max Range: 3.7809. Min Range: -3.7809

Max Act: 3.7157. Min Act: -0.1700

Data Index: 4326930 (Open Web Text)

Max Activating Token Index: 201

Text #3

Max Range: 3.7809. Min Range: -3.7809

Max Act: 3.7239. Min Act: -0.1700

Data Index: 6578949 (Open Web Text)

Max Activating Token Index: 793

Text #4

Max Range: 3.7809. Min Range: -3.7809

Max Act: 3.7143. Min Act: -0.1700

Data Index: 7700457 (Open Web Text)

Max Activating Token Index: 845

Text #5

Max Range: 3.7809. Min Range: -3.7809

Max Act: 3.6938. Min Act: -0.1700

Data Index: 1910306 (Open Web Text)

Max Activating Token Index: 634

Text #6

Max Range: 3.7809. Min Range: -3.7809

Max Act: 3.6716. Min Act: -0.1700

Data Index: 1206955 (Open Web Text)

Max Activating Token Index: 588

Text #7

Max Range: 3.7809. Min Range: -3.7809

Max Act: 3.6670. Min Act: -0.1700

Data Index: 6968292 (Open Web Text)

Max Activating Token Index: 1005

Text #8

Max Range: 3.7809. Min Range: -3.7809

Max Act: 3.6545. Min Act: -0.1700

Data Index: 254318 (Open Web Text)

Max Activating Token Index: 532

Text #9

Max Range: 3.7809. Min Range: -3.7809

Max Act: 3.6503. Min Act: -0.1700

Data Index: 7966966 (Open Web Text)

Max Activating Token Index: 312

Text #10

Max Range: 3.7809. Min Range: -3.7809

Max Act: 3.6459. Min Act: -0.1700

Data Index: 4986440 (Open Web Text)

Max Activating Token Index: 992

Text #11

Max Range: 3.7809. Min Range: -3.7809

Max Act: 3.6261. Min Act: -0.1700

Data Index: 1632345 (Open Web Text)

Max Activating Token Index: 729

Text #12

Max Range: 3.7809. Min Range: -3.7809

Max Act: 3.6285. Min Act: -0.1700

Data Index: 4942954 (Open Web Text)

Max Activating Token Index: 622

Text #13

Max Range: 3.7809. Min Range: -3.7809

Max Act: 3.6220. Min Act: -0.1700

Data Index: 4328224 (Open Web Text)

Max Activating Token Index: 325

Text #14

Max Range: 3.7809. Min Range: -3.7809

Max Act: 3.6044. Min Act: -0.1700

Data Index: 1495018 (Open Web Text)

Max Activating Token Index: 721

Text #15

Max Range: 3.7809. Min Range: -3.7809

Max Act: 3.6188. Min Act: -0.1700

Data Index: 2127552 (Open Web Text)

Max Activating Token Index: 58

Text #16

Max Range: 3.7809. Min Range: -3.7809

Max Act: 3.5993. Min Act: -0.1700

Data Index: 2799288 (Open Web Text)

Max Activating Token Index: 1015

Text #17

Max Range: 3.7809. Min Range: -3.7809

Max Act: 3.6060. Min Act: -0.1700

Data Index: 4119764 (Open Web Text)

Max Activating Token Index: 181

Text #18

Max Range: 3.7809. Min Range: -3.7809

Max Act: 3.5739. Min Act: -0.1700

Data Index: 3175044 (Open Web Text)

Max Activating Token Index: 417

Text #19

Max Range: 3.7809. Min Range: -3.7809

Max Act: 3.5810. Min Act: -0.1700

Data Index: 3267709 (Open Web Text)

Max Activating Token Index: 259