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

Dataset: Open Web Text

Neuron 2964 in Layer 1

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: 1.9808. Min Range: -1.9808

Max Act: 1.9808. Min Act: -0.1700

Data Index: 7897757 (Open Web Text)

Max Activating Token Index: 615

Text #1

Max Range: 1.9808. Min Range: -1.9808

Max Act: 1.9677. Min Act: -0.1684

Data Index: 157671 (Open Web Text)

Max Activating Token Index: 1022

Text #2

Max Range: 1.9808. Min Range: -1.9808

Max Act: 1.9226. Min Act: -0.1700

Data Index: 460428 (Open Web Text)

Max Activating Token Index: 603

Text #3

Max Range: 1.9808. Min Range: -1.9808

Max Act: 1.9182. Min Act: -0.1700

Data Index: 5952207 (Open Web Text)

Max Activating Token Index: 114

Text #4

Max Range: 1.9808. Min Range: -1.9808

Max Act: 1.9134. Min Act: -0.1700

Data Index: 2658136 (Open Web Text)

Max Activating Token Index: 216

Text #5

Max Range: 1.9808. Min Range: -1.9808

Max Act: 1.8647. Min Act: -0.1700

Data Index: 516880 (Open Web Text)

Max Activating Token Index: 516

Text #6

Max Range: 1.9808. Min Range: -1.9808

Max Act: 1.8627. Min Act: -0.1700

Data Index: 5952204 (Open Web Text)

Max Activating Token Index: 619

Text #7

Max Range: 1.9808. Min Range: -1.9808

Max Act: 1.8795. Min Act: -0.1700

Data Index: 2658134 (Open Web Text)

Max Activating Token Index: 618

Text #8

Max Range: 1.9808. Min Range: -1.9808

Max Act: 1.8577. Min Act: -0.1700

Data Index: 8528092 (Open Web Text)

Max Activating Token Index: 512

Text #9

Max Range: 1.9808. Min Range: -1.9808

Max Act: 1.8535. Min Act: -0.1699

Data Index: 4047858 (Open Web Text)

Max Activating Token Index: 623

Text #10

Max Range: 1.9808. Min Range: -1.9808

Max Act: 1.8378. Min Act: -0.1697

Data Index: 3696779 (Open Web Text)

Max Activating Token Index: 980

Text #11

Max Range: 1.9808. Min Range: -1.9808

Max Act: 1.8342. Min Act: -0.1700

Data Index: 6454112 (Open Web Text)

Max Activating Token Index: 965

Text #12

Max Range: 1.9808. Min Range: -1.9808

Max Act: 1.8297. Min Act: -0.1700

Data Index: 4328214 (Open Web Text)

Max Activating Token Index: 169

Text #13

Max Range: 1.9808. Min Range: -1.9808

Max Act: 1.8310. Min Act: -0.1700

Data Index: 7767869 (Open Web Text)

Max Activating Token Index: 770

Text #14

Max Range: 1.9808. Min Range: -1.9808

Max Act: 1.8274. Min Act: -0.1700

Data Index: 6651376 (Open Web Text)

Max Activating Token Index: 126

Text #15

Max Range: 1.9808. Min Range: -1.9808

Max Act: 1.8186. Min Act: -0.1700

Data Index: 7897755 (Open Web Text)

Max Activating Token Index: 63

Text #16

Max Range: 1.9808. Min Range: -1.9808

Max Act: 1.8187. Min Act: -0.1700

Data Index: 6257356 (Open Web Text)

Max Activating Token Index: 465

Text #17

Max Range: 1.9808. Min Range: -1.9808

Max Act: 1.8214. Min Act: -0.1700

Data Index: 5066571 (Open Web Text)

Max Activating Token Index: 583

Text #18

Max Range: 1.9808. Min Range: -1.9808

Max Act: 1.8158. Min Act: -0.1700

Data Index: 8573449 (Open Web Text)

Max Activating Token Index: 197

Text #19

Max Range: 1.9808. Min Range: -1.9808

Max Act: 1.8107. Min Act: -0.1700

Data Index: 7283721 (Open Web Text)

Max Activating Token Index: 435