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

Dataset: Open Web Text

Neuron 1602 in Layer 6

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: 3.2206. Min Range: -3.2206

Max Act: 3.2206. Min Act: -0.1700

Data Index: 6024369 (Open Web Text)

Max Activating Token Index: 427

Text #1

Max Range: 3.2206. Min Range: -3.2206

Max Act: 3.1328. Min Act: -0.1700

Data Index: 5372281 (Open Web Text)

Max Activating Token Index: 531

Text #2

Max Range: 3.2206. Min Range: -3.2206

Max Act: 3.1110. Min Act: -0.1700

Data Index: 3348020 (Open Web Text)

Max Activating Token Index: 91

Text #3

Max Range: 3.2206. Min Range: -3.2206

Max Act: 3.0824. Min Act: -0.1700

Data Index: 6655789 (Open Web Text)

Max Activating Token Index: 600

Text #4

Max Range: 3.2206. Min Range: -3.2206

Max Act: 3.0332. Min Act: -0.1700

Data Index: 2288370 (Open Web Text)

Max Activating Token Index: 860

Text #5

Max Range: 3.2206. Min Range: -3.2206

Max Act: 3.0290. Min Act: -0.1700

Data Index: 3006930 (Open Web Text)

Max Activating Token Index: 293

Text #6

Max Range: 3.2206. Min Range: -3.2206

Max Act: 3.0439. Min Act: -0.1700

Data Index: 8797786 (Open Web Text)

Max Activating Token Index: 898

Text #7

Max Range: 3.2206. Min Range: -3.2206

Max Act: 3.0114. Min Act: -0.1700

Data Index: 4441932 (Open Web Text)

Max Activating Token Index: 626

Text #8

Max Range: 3.2206. Min Range: -3.2206

Max Act: 3.0318. Min Act: -0.1700

Data Index: 1326898 (Open Web Text)

Max Activating Token Index: 560

Text #9

Max Range: 3.2206. Min Range: -3.2206

Max Act: 3.0101. Min Act: -0.1700

Data Index: 549324 (Open Web Text)

Max Activating Token Index: 227

Text #10

Max Range: 3.2206. Min Range: -3.2206

Max Act: 3.0227. Min Act: -0.1700

Data Index: 1988202 (Open Web Text)

Max Activating Token Index: 245

Text #11

Max Range: 3.2206. Min Range: -3.2206

Max Act: 3.0219. Min Act: -0.1700

Data Index: 7529370 (Open Web Text)

Max Activating Token Index: 824

Text #12

Max Range: 3.2206. Min Range: -3.2206

Max Act: 3.0056. Min Act: -0.1700

Data Index: 5878913 (Open Web Text)

Max Activating Token Index: 213

Text #13

Max Range: 3.2206. Min Range: -3.2206

Max Act: 3.0082. Min Act: -0.1700

Data Index: 5290500 (Open Web Text)

Max Activating Token Index: 403

Text #14

Max Range: 3.2206. Min Range: -3.2206

Max Act: 2.9846. Min Act: -0.1700

Data Index: 2638861 (Open Web Text)

Max Activating Token Index: 1020

Text #15

Max Range: 3.2206. Min Range: -3.2206

Max Act: 2.9917. Min Act: -0.1700

Data Index: 4449137 (Open Web Text)

Max Activating Token Index: 564

Text #16

Max Range: 3.2206. Min Range: -3.2206

Max Act: 2.9722. Min Act: -0.1700

Data Index: 6566093 (Open Web Text)

Max Activating Token Index: 204

Text #17

Max Range: 3.2206. Min Range: -3.2206

Max Act: 2.9756. Min Act: -0.1700

Data Index: 2148957 (Open Web Text)

Max Activating Token Index: 920

Text #18

Max Range: 3.2206. Min Range: -3.2206

Max Act: 2.9683. Min Act: -0.1700

Data Index: 1752331 (Open Web Text)

Max Activating Token Index: 752

Text #19

Max Range: 3.2206. Min Range: -3.2206

Max Act: 2.9679. Min Act: -0.1700

Data Index: 4301925 (Open Web Text)

Max Activating Token Index: 748