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

Dataset: Open Web Text

Neuron 2885 in Layer 4

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: 4.3174. Min Range: -4.3174

Max Act: 4.3053. Min Act: -0.1700

Data Index: 5847753 (Open Web Text)

Max Activating Token Index: 21

Text #1

Max Range: 4.3174. Min Range: -4.3174

Max Act: 4.3174. Min Act: -0.1700

Data Index: 8708178 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 4.3174. Min Range: -4.3174

Max Act: 4.2414. Min Act: -0.1700

Data Index: 5842014 (Open Web Text)

Max Activating Token Index: 773

Text #3

Max Range: 4.3174. Min Range: -4.3174

Max Act: 4.1449. Min Act: -0.1700

Data Index: 6254953 (Open Web Text)

Max Activating Token Index: 22

Text #4

Max Range: 4.3174. Min Range: -4.3174

Max Act: 4.1385. Min Act: -0.1700

Data Index: 174051 (Open Web Text)

Max Activating Token Index: 502

Text #5

Max Range: 4.3174. Min Range: -4.3174

Max Act: 4.1377. Min Act: -0.1700

Data Index: 2139384 (Open Web Text)

Max Activating Token Index: 774

Text #6

Max Range: 4.3174. Min Range: -4.3174

Max Act: 4.1286. Min Act: -0.1700

Data Index: 6490078 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 4.3174. Min Range: -4.3174

Max Act: 4.1007. Min Act: -0.1700

Data Index: 1554609 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 4.3174. Min Range: -4.3174

Max Act: 4.0809. Min Act: -0.1700

Data Index: 3517488 (Open Web Text)

Max Activating Token Index: 646

Text #9

Max Range: 4.3174. Min Range: -4.3174

Max Act: 4.0612. Min Act: -0.1700

Data Index: 1479509 (Open Web Text)

Max Activating Token Index: 953

Text #10

Max Range: 4.3174. Min Range: -4.3174

Max Act: 4.0688. Min Act: -0.1700

Data Index: 928177 (Open Web Text)

Max Activating Token Index: 926

Text #11

Max Range: 4.3174. Min Range: -4.3174

Max Act: 4.1183. Min Act: -0.1700

Data Index: 2214175 (Open Web Text)

Max Activating Token Index: 931

Text #12

Max Range: 4.3174. Min Range: -4.3174

Max Act: 4.0375. Min Act: -0.1700

Data Index: 2473648 (Open Web Text)

Max Activating Token Index: 688

Text #13

Max Range: 4.3174. Min Range: -4.3174

Max Act: 4.1168. Min Act: -0.1700

Data Index: 3721003 (Open Web Text)

Max Activating Token Index: 1015

Text #14

Max Range: 4.3174. Min Range: -4.3174

Max Act: 4.0215. Min Act: -0.1700

Data Index: 480748 (Open Web Text)

Max Activating Token Index: 898

Text #15

Max Range: 4.3174. Min Range: -4.3174

Max Act: 4.0785. Min Act: -0.1700

Data Index: 631592 (Open Web Text)

Max Activating Token Index: 848

Text #16

Max Range: 4.3174. Min Range: -4.3174

Max Act: 4.0730. Min Act: -0.1700

Data Index: 872287 (Open Web Text)

Max Activating Token Index: 30

Text #17

Max Range: 4.3174. Min Range: -4.3174

Max Act: 4.0678. Min Act: -0.1700

Data Index: 3695951 (Open Web Text)

Max Activating Token Index: 686

Text #18

Max Range: 4.3174. Min Range: -4.3174

Max Act: 4.0569. Min Act: -0.1700

Data Index: 1251043 (Open Web Text)

Max Activating Token Index: 21

Text #19

Max Range: 4.3174. Min Range: -4.3174

Max Act: 4.0463. Min Act: -0.1700

Data Index: 3560062 (Open Web Text)

Max Activating Token Index: 171