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

Dataset: Open Web Text

Neuron 2631 in Layer 5

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: 2.9119. Min Range: -2.9119

Max Act: 2.9119. Min Act: -0.1700

Data Index: 6745574 (Open Web Text)

Max Activating Token Index: 738

Text #1

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.8518. Min Act: -0.1700

Data Index: 5820176 (Open Web Text)

Max Activating Token Index: 488

Text #2

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.8375. Min Act: -0.1700

Data Index: 3017958 (Open Web Text)

Max Activating Token Index: 516

Text #3

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.8425. Min Act: -0.1700

Data Index: 6116949 (Open Web Text)

Max Activating Token Index: 627

Text #4

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.8272. Min Act: -0.1700

Data Index: 1302937 (Open Web Text)

Max Activating Token Index: 28

Text #5

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.8207. Min Act: -0.1700

Data Index: 5707190 (Open Web Text)

Max Activating Token Index: 425

Text #6

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.8119. Min Act: -0.1700

Data Index: 6746874 (Open Web Text)

Max Activating Token Index: 875

Text #7

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.7764. Min Act: -0.1700

Data Index: 8807452 (Open Web Text)

Max Activating Token Index: 37

Text #8

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.7781. Min Act: -0.1700

Data Index: 919749 (Open Web Text)

Max Activating Token Index: 209

Text #9

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.7559. Min Act: -0.1700

Data Index: 5667607 (Open Web Text)

Max Activating Token Index: 74

Text #10

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.7684. Min Act: -0.1700

Data Index: 8013071 (Open Web Text)

Max Activating Token Index: 918

Text #11

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.7446. Min Act: -0.1700

Data Index: 1126263 (Open Web Text)

Max Activating Token Index: 305

Text #12

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.7328. Min Act: -0.1700

Data Index: 8043354 (Open Web Text)

Max Activating Token Index: 188

Text #13

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.7183. Min Act: -0.1700

Data Index: 4174077 (Open Web Text)

Max Activating Token Index: 379

Text #14

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.7159. Min Act: -0.1700

Data Index: 6971041 (Open Web Text)

Max Activating Token Index: 778

Text #15

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.7041. Min Act: -0.1700

Data Index: 3454519 (Open Web Text)

Max Activating Token Index: 598

Text #16

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.7181. Min Act: -0.1700

Data Index: 5882996 (Open Web Text)

Max Activating Token Index: 229

Text #17

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.7050. Min Act: -0.1700

Data Index: 2749965 (Open Web Text)

Max Activating Token Index: 811

Text #18

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.7005. Min Act: -0.1700

Data Index: 6459424 (Open Web Text)

Max Activating Token Index: 847

Text #19

Max Range: 2.9119. Min Range: -2.9119

Max Act: 2.7177. Min Act: -0.1700

Data Index: 7352701 (Open Web Text)

Max Activating Token Index: 28