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

Dataset: Open Web Text

Neuron 2575 in Layer 6

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: 4.0810. Min Range: -4.0810

Max Act: 4.0810. Min Act: -0.1700

Data Index: 8470827 (Open Web Text)

Max Activating Token Index: 717

Text #1

Max Range: 4.0810. Min Range: -4.0810

Max Act: 4.0625. Min Act: -0.1700

Data Index: 5496777 (Open Web Text)

Max Activating Token Index: 951

Text #2

Max Range: 4.0810. Min Range: -4.0810

Max Act: 4.0614. Min Act: -0.1700

Data Index: 1528106 (Open Web Text)

Max Activating Token Index: 837

Text #3

Max Range: 4.0810. Min Range: -4.0810

Max Act: 4.0759. Min Act: -0.1700

Data Index: 6016546 (Open Web Text)

Max Activating Token Index: 873

Text #4

Max Range: 4.0810. Min Range: -4.0810

Max Act: 4.0046. Min Act: -0.1700

Data Index: 8128056 (Open Web Text)

Max Activating Token Index: 590

Text #5

Max Range: 4.0810. Min Range: -4.0810

Max Act: 4.0135. Min Act: -0.1700

Data Index: 4952180 (Open Web Text)

Max Activating Token Index: 834

Text #6

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.9950. Min Act: -0.1700

Data Index: 5152593 (Open Web Text)

Max Activating Token Index: 796

Text #7

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.9244. Min Act: -0.1700

Data Index: 1330181 (Open Web Text)

Max Activating Token Index: 925

Text #8

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.8751. Min Act: -0.1700

Data Index: 5700879 (Open Web Text)

Max Activating Token Index: 1011

Text #9

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.8682. Min Act: -0.1700

Data Index: 8763575 (Open Web Text)

Max Activating Token Index: 189

Text #10

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.8573. Min Act: -0.1700

Data Index: 5576008 (Open Web Text)

Max Activating Token Index: 729

Text #11

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.8366. Min Act: -0.1700

Data Index: 4392209 (Open Web Text)

Max Activating Token Index: 666

Text #12

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.8731. Min Act: -0.1700

Data Index: 5334114 (Open Web Text)

Max Activating Token Index: 910

Text #13

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.8404. Min Act: -0.1700

Data Index: 4663630 (Open Web Text)

Max Activating Token Index: 803

Text #14

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.8049. Min Act: -0.1700

Data Index: 4125111 (Open Web Text)

Max Activating Token Index: 229

Text #15

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.8232. Min Act: -0.1700

Data Index: 4987325 (Open Web Text)

Max Activating Token Index: 362

Text #16

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.8154. Min Act: -0.1700

Data Index: 4481191 (Open Web Text)

Max Activating Token Index: 712

Text #17

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.7839. Min Act: -0.1700

Data Index: 3209504 (Open Web Text)

Max Activating Token Index: 158

Text #18

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.7785. Min Act: -0.1700

Data Index: 2055695 (Open Web Text)

Max Activating Token Index: 482

Text #19

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.8093. Min Act: -0.1700

Data Index: 2268961 (Open Web Text)

Max Activating Token Index: 805