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

Dataset: Open Web Text

Neuron 1725 in Layer 0

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: 3.7056. Min Range: -3.7056

Max Act: 3.7056. Min Act: -0.1700

Data Index: 3735945 (Open Web Text)

Max Activating Token Index: 846

Text #1

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.4766. Min Act: -0.1700

Data Index: 1203839 (Open Web Text)

Max Activating Token Index: 986

Text #2

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.4188. Min Act: -0.1700

Data Index: 2529721 (Open Web Text)

Max Activating Token Index: 698

Text #3

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.3678. Min Act: -0.1700

Data Index: 1800716 (Open Web Text)

Max Activating Token Index: 311

Text #4

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.3422. Min Act: -0.1700

Data Index: 3364258 (Open Web Text)

Max Activating Token Index: 547

Text #5

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.3376. Min Act: -0.1494

Data Index: 256520 (Open Web Text)

Max Activating Token Index: 90

Text #6

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.3078. Min Act: -0.1700

Data Index: 5615468 (Open Web Text)

Max Activating Token Index: 58

Text #7

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.2663. Min Act: -0.1700

Data Index: 6346562 (Open Web Text)

Max Activating Token Index: 20

Text #8

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.2917. Min Act: -0.1700

Data Index: 2030722 (Open Web Text)

Max Activating Token Index: 791

Text #9

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.2334. Min Act: -0.1700

Data Index: 1160997 (Open Web Text)

Max Activating Token Index: 377

Text #10

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.2514. Min Act: -0.1700

Data Index: 6506168 (Open Web Text)

Max Activating Token Index: 750

Text #11

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.2295. Min Act: -0.1700

Data Index: 5589072 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.2295. Min Act: -0.1700

Data Index: 5782812 (Open Web Text)

Max Activating Token Index: 159

Text #13

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.2233. Min Act: -0.1700

Data Index: 6277859 (Open Web Text)

Max Activating Token Index: 51

Text #14

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.2015. Min Act: -0.1700

Data Index: 6641566 (Open Web Text)

Max Activating Token Index: 864

Text #15

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.2190. Min Act: -0.1700

Data Index: 6665369 (Open Web Text)

Max Activating Token Index: 985

Text #16

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.2001. Min Act: -0.1700

Data Index: 256524 (Open Web Text)

Max Activating Token Index: 68

Text #17

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.1685. Min Act: -0.1700

Data Index: 6345527 (Open Web Text)

Max Activating Token Index: 367

Text #18

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.1827. Min Act: -0.1700

Data Index: 2740082 (Open Web Text)

Max Activating Token Index: 201

Text #19

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.1880. Min Act: -0.1700

Data Index: 2850743 (Open Web Text)

Max Activating Token Index: 495