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

Dataset: Open Web Text

Neuron 962 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: 6.2034. Min Range: -6.2034

Max Act: 6.2034. Min Act: -0.1700

Data Index: 4308074 (Open Web Text)

Max Activating Token Index: 59

Text #1

Max Range: 6.2034. Min Range: -6.2034

Max Act: 6.1621. Min Act: -0.1700

Data Index: 3536385 (Open Web Text)

Max Activating Token Index: 101

Text #2

Max Range: 6.2034. Min Range: -6.2034

Max Act: 6.0908. Min Act: -0.1700

Data Index: 2676121 (Open Web Text)

Max Activating Token Index: 727

Text #3

Max Range: 6.2034. Min Range: -6.2034

Max Act: 5.8062. Min Act: -0.1700

Data Index: 1509563 (Open Web Text)

Max Activating Token Index: 721

Text #4

Max Range: 6.2034. Min Range: -6.2034

Max Act: 5.8630. Min Act: -0.1700

Data Index: 366969 (Open Web Text)

Max Activating Token Index: 66

Text #5

Max Range: 6.2034. Min Range: -6.2034

Max Act: 5.8044. Min Act: -0.1700

Data Index: 2838636 (Open Web Text)

Max Activating Token Index: 901

Text #6

Max Range: 6.2034. Min Range: -6.2034

Max Act: 5.7647. Min Act: -0.1700

Data Index: 3485029 (Open Web Text)

Max Activating Token Index: 398

Text #7

Max Range: 6.2034. Min Range: -6.2034

Max Act: 5.7190. Min Act: -0.1700

Data Index: 3030637 (Open Web Text)

Max Activating Token Index: 609

Text #8

Max Range: 6.2034. Min Range: -6.2034

Max Act: 5.6322. Min Act: -0.1700

Data Index: 4295405 (Open Web Text)

Max Activating Token Index: 90

Text #9

Max Range: 6.2034. Min Range: -6.2034

Max Act: 5.5270. Min Act: -0.1700

Data Index: 3536383 (Open Web Text)

Max Activating Token Index: 843

Text #10

Max Range: 6.2034. Min Range: -6.2034

Max Act: 5.6471. Min Act: -0.1700

Data Index: 651013 (Open Web Text)

Max Activating Token Index: 220

Text #11

Max Range: 6.2034. Min Range: -6.2034

Max Act: 5.6452. Min Act: -0.1700

Data Index: 7948065 (Open Web Text)

Max Activating Token Index: 901

Text #12

Max Range: 6.2034. Min Range: -6.2034

Max Act: 5.6542. Min Act: -0.1700

Data Index: 7162959 (Open Web Text)

Max Activating Token Index: 566

Text #13

Max Range: 6.2034. Min Range: -6.2034

Max Act: 5.6324. Min Act: -0.1700

Data Index: 6232821 (Open Web Text)

Max Activating Token Index: 690

Text #14

Max Range: 6.2034. Min Range: -6.2034

Max Act: 5.5888. Min Act: -0.1700

Data Index: 5472095 (Open Web Text)

Max Activating Token Index: 70

Text #15

Max Range: 6.2034. Min Range: -6.2034

Max Act: 5.6744. Min Act: -0.1700

Data Index: 6512636 (Open Web Text)

Max Activating Token Index: 176

Text #16

Max Range: 6.2034. Min Range: -6.2034

Max Act: 5.6303. Min Act: -0.1700

Data Index: 2156703 (Open Web Text)

Max Activating Token Index: 132

Text #17

Max Range: 6.2034. Min Range: -6.2034

Max Act: 5.5916. Min Act: -0.1700

Data Index: 7555172 (Open Web Text)

Max Activating Token Index: 945

Text #18

Max Range: 6.2034. Min Range: -6.2034

Max Act: 5.5888. Min Act: -0.1700

Data Index: 6232832 (Open Web Text)

Max Activating Token Index: 778

Text #19

Max Range: 6.2034. Min Range: -6.2034

Max Act: 5.5549. Min Act: -0.1700

Data Index: 7310640 (Open Web Text)

Max Activating Token Index: 212