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

Dataset: Open Web Text

Neuron 1068 in Layer 3

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: 3.6236. Min Range: -3.6236

Max Act: 3.6236. Min Act: -0.1700

Data Index: 4386746 (Open Web Text)

Max Activating Token Index: 897

Text #1

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.5814. Min Act: -0.1700

Data Index: 4386747 (Open Web Text)

Max Activating Token Index: 230

Text #2

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.4387. Min Act: -0.1700

Data Index: 1079593 (Open Web Text)

Max Activating Token Index: 483

Text #3

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.4148. Min Act: -0.1700

Data Index: 2834982 (Open Web Text)

Max Activating Token Index: 220

Text #4

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.3879. Min Act: -0.1700

Data Index: 8249937 (Open Web Text)

Max Activating Token Index: 575

Text #5

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.3899. Min Act: -0.1700

Data Index: 4561016 (Open Web Text)

Max Activating Token Index: 429

Text #6

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.3622. Min Act: -0.1700

Data Index: 1169752 (Open Web Text)

Max Activating Token Index: 353

Text #7

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.3722. Min Act: -0.1700

Data Index: 7808186 (Open Web Text)

Max Activating Token Index: 636

Text #8

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.2922. Min Act: -0.1700

Data Index: 3054697 (Open Web Text)

Max Activating Token Index: 773

Text #9

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.3053. Min Act: -0.1700

Data Index: 1681263 (Open Web Text)

Max Activating Token Index: 896

Text #10

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.3365. Min Act: -0.1700

Data Index: 4540358 (Open Web Text)

Max Activating Token Index: 37

Text #11

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.2873. Min Act: -0.1700

Data Index: 2443635 (Open Web Text)

Max Activating Token Index: 765

Text #12

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.2919. Min Act: -0.1700

Data Index: 8289875 (Open Web Text)

Max Activating Token Index: 980

Text #13

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.2659. Min Act: -0.1700

Data Index: 2246858 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.2659. Min Act: -0.1700

Data Index: 3043014 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.2659. Min Act: -0.1700

Data Index: 3052306 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.2659. Min Act: -0.1700

Data Index: 3124567 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.2543. Min Act: -0.1700

Data Index: 2891254 (Open Web Text)

Max Activating Token Index: 422

Text #18

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.2235. Min Act: -0.1700

Data Index: 6669905 (Open Web Text)

Max Activating Token Index: 756

Text #19

Max Range: 3.6236. Min Range: -3.6236

Max Act: 3.2210. Min Act: -0.1700

Data Index: 7566204 (Open Web Text)

Max Activating Token Index: 424