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

Dataset: Open Web Text

Neuron 1244 in Layer 2

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: 4.7764. Min Range: -4.7764

Max Act: 4.7764. Min Act: -0.1700

Data Index: 1550952 (Open Web Text)

Max Activating Token Index: 579

Text #1

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.7375. Min Act: -0.1700

Data Index: 323118 (Open Web Text)

Max Activating Token Index: 487

Text #2

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.6936. Min Act: -0.1700

Data Index: 5747651 (Open Web Text)

Max Activating Token Index: 405

Text #3

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.6728. Min Act: -0.1700

Data Index: 6148852 (Open Web Text)

Max Activating Token Index: 214

Text #4

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.6949. Min Act: -0.1700

Data Index: 7050242 (Open Web Text)

Max Activating Token Index: 102

Text #5

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.6822. Min Act: -0.1700

Data Index: 1140377 (Open Web Text)

Max Activating Token Index: 20

Text #6

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.6584. Min Act: -0.1700

Data Index: 8171609 (Open Web Text)

Max Activating Token Index: 490

Text #7

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.6633. Min Act: -0.1700

Data Index: 141058 (Open Web Text)

Max Activating Token Index: 188

Text #8

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.6540. Min Act: -0.1700

Data Index: 3407674 (Open Web Text)

Max Activating Token Index: 560

Text #9

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.5928. Min Act: -0.1700

Data Index: 4377230 (Open Web Text)

Max Activating Token Index: 966

Text #10

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.6326. Min Act: -0.1700

Data Index: 7804782 (Open Web Text)

Max Activating Token Index: 701

Text #11

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.5961. Min Act: -0.1700

Data Index: 8391080 (Open Web Text)

Max Activating Token Index: 354

Text #12

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.5940. Min Act: -0.1700

Data Index: 22017 (Open Web Text)

Max Activating Token Index: 551

Text #13

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.5927. Min Act: -0.1700

Data Index: 7813541 (Open Web Text)

Max Activating Token Index: 220

Text #14

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.5990. Min Act: -0.1700

Data Index: 2268337 (Open Web Text)

Max Activating Token Index: 153

Text #15

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.6045. Min Act: -0.1700

Data Index: 6035516 (Open Web Text)

Max Activating Token Index: 111

Text #16

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.5776. Min Act: -0.1700

Data Index: 5806778 (Open Web Text)

Max Activating Token Index: 59

Text #17

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.5893. Min Act: -0.1700

Data Index: 363714 (Open Web Text)

Max Activating Token Index: 431

Text #18

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.5655. Min Act: -0.1700

Data Index: 4900225 (Open Web Text)

Max Activating Token Index: 1020

Text #19

Max Range: 4.7764. Min Range: -4.7764

Max Act: 4.6163. Min Act: -0.1700

Data Index: 3693104 (Open Web Text)

Max Activating Token Index: 885