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

Dataset: Open Web Text

Neuron 417 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: 5.1129. Min Range: -5.1129

Max Act: 5.1129. Min Act: -0.1700

Data Index: 6881862 (Open Web Text)

Max Activating Token Index: 936

Text #1

Max Range: 5.1129. Min Range: -5.1129

Max Act: 5.1002. Min Act: -0.1700

Data Index: 477154 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.1129. Min Range: -5.1129

Max Act: 5.0708. Min Act: -0.1700

Data Index: 4664245 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 5.1129. Min Range: -5.1129

Max Act: 5.0099. Min Act: -0.1700

Data Index: 2114684 (Open Web Text)

Max Activating Token Index: 967

Text #4

Max Range: 5.1129. Min Range: -5.1129

Max Act: 5.0031. Min Act: -0.1700

Data Index: 6185996 (Open Web Text)

Max Activating Token Index: 931

Text #5

Max Range: 5.1129. Min Range: -5.1129

Max Act: 5.0065. Min Act: -0.1700

Data Index: 1043689 (Open Web Text)

Max Activating Token Index: 774

Text #6

Max Range: 5.1129. Min Range: -5.1129

Max Act: 5.0022. Min Act: -0.1700

Data Index: 7044872 (Open Web Text)

Max Activating Token Index: 890

Text #7

Max Range: 5.1129. Min Range: -5.1129

Max Act: 5.0200. Min Act: -0.1700

Data Index: 4705574 (Open Web Text)

Max Activating Token Index: 861

Text #8

Max Range: 5.1129. Min Range: -5.1129

Max Act: 4.9701. Min Act: -0.1700

Data Index: 5289485 (Open Web Text)

Max Activating Token Index: 798

Text #9

Max Range: 5.1129. Min Range: -5.1129

Max Act: 4.9896. Min Act: -0.1700

Data Index: 5960831 (Open Web Text)

Max Activating Token Index: 994

Text #10

Max Range: 5.1129. Min Range: -5.1129

Max Act: 4.9765. Min Act: -0.1700

Data Index: 4884795 (Open Web Text)

Max Activating Token Index: 837

Text #11

Max Range: 5.1129. Min Range: -5.1129

Max Act: 4.9966. Min Act: -0.1700

Data Index: 8507971 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 5.1129. Min Range: -5.1129

Max Act: 4.9700. Min Act: -0.1700

Data Index: 1116563 (Open Web Text)

Max Activating Token Index: 878

Text #13

Max Range: 5.1129. Min Range: -5.1129

Max Act: 4.9872. Min Act: -0.1700

Data Index: 4277019 (Open Web Text)

Max Activating Token Index: 938

Text #14

Max Range: 5.1129. Min Range: -5.1129

Max Act: 4.9744. Min Act: -0.1700

Data Index: 2911044 (Open Web Text)

Max Activating Token Index: 919

Text #15

Max Range: 5.1129. Min Range: -5.1129

Max Act: 4.9772. Min Act: -0.1700

Data Index: 56688 (Open Web Text)

Max Activating Token Index: 812

Text #16

Max Range: 5.1129. Min Range: -5.1129

Max Act: 4.9788. Min Act: -0.1700

Data Index: 6044089 (Open Web Text)

Max Activating Token Index: 862

Text #17

Max Range: 5.1129. Min Range: -5.1129

Max Act: 4.9343. Min Act: -0.1700

Data Index: 1841499 (Open Web Text)

Max Activating Token Index: 1006

Text #18

Max Range: 5.1129. Min Range: -5.1129

Max Act: 4.9836. Min Act: -0.1700

Data Index: 1177181 (Open Web Text)

Max Activating Token Index: 1009

Text #19

Max Range: 5.1129. Min Range: -5.1129

Max Act: 4.9737. Min Act: -0.1700

Data Index: 5142604 (Open Web Text)

Max Activating Token Index: 944