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

Dataset: Open Web Text

Neuron 699 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: 4.4040. Min Range: -4.4040

Max Act: 4.3971. Min Act: -0.1700

Data Index: 4940978 (Open Web Text)

Max Activating Token Index: 680

Text #1

Max Range: 4.4040. Min Range: -4.4040

Max Act: 4.3597. Min Act: -0.1700

Data Index: 6708456 (Open Web Text)

Max Activating Token Index: 960

Text #2

Max Range: 4.4040. Min Range: -4.4040

Max Act: 4.4040. Min Act: -0.1700

Data Index: 3442042 (Open Web Text)

Max Activating Token Index: 417

Text #3

Max Range: 4.4040. Min Range: -4.4040

Max Act: 4.3693. Min Act: -0.1700

Data Index: 6782253 (Open Web Text)

Max Activating Token Index: 552

Text #4

Max Range: 4.4040. Min Range: -4.4040

Max Act: 4.3503. Min Act: -0.1700

Data Index: 6335397 (Open Web Text)

Max Activating Token Index: 52

Text #5

Max Range: 4.4040. Min Range: -4.4040

Max Act: 4.3571. Min Act: -0.1700

Data Index: 8718062 (Open Web Text)

Max Activating Token Index: 626

Text #6

Max Range: 4.4040. Min Range: -4.4040

Max Act: 4.3392. Min Act: -0.1700

Data Index: 3087705 (Open Web Text)

Max Activating Token Index: 808

Text #7

Max Range: 4.4040. Min Range: -4.4040

Max Act: 4.3074. Min Act: -0.1700

Data Index: 2117405 (Open Web Text)

Max Activating Token Index: 511

Text #8

Max Range: 4.4040. Min Range: -4.4040

Max Act: 4.3223. Min Act: -0.1700

Data Index: 5121407 (Open Web Text)

Max Activating Token Index: 748

Text #9

Max Range: 4.4040. Min Range: -4.4040

Max Act: 4.2984. Min Act: -0.1700

Data Index: 2346304 (Open Web Text)

Max Activating Token Index: 986

Text #10

Max Range: 4.4040. Min Range: -4.4040

Max Act: 4.2696. Min Act: -0.1700

Data Index: 8461166 (Open Web Text)

Max Activating Token Index: 813

Text #11

Max Range: 4.4040. Min Range: -4.4040

Max Act: 4.2594. Min Act: -0.1700

Data Index: 6045493 (Open Web Text)

Max Activating Token Index: 881

Text #12

Max Range: 4.4040. Min Range: -4.4040

Max Act: 4.2992. Min Act: -0.1700

Data Index: 3037120 (Open Web Text)

Max Activating Token Index: 430

Text #13

Max Range: 4.4040. Min Range: -4.4040

Max Act: 4.2363. Min Act: -0.1700

Data Index: 7770484 (Open Web Text)

Max Activating Token Index: 963

Text #14

Max Range: 4.4040. Min Range: -4.4040

Max Act: 4.2582. Min Act: -0.1700

Data Index: 4439286 (Open Web Text)

Max Activating Token Index: 45

Text #15

Max Range: 4.4040. Min Range: -4.4040

Max Act: 4.2414. Min Act: -0.1700

Data Index: 1286305 (Open Web Text)

Max Activating Token Index: 673

Text #16

Max Range: 4.4040. Min Range: -4.4040

Max Act: 4.2141. Min Act: -0.1700

Data Index: 7542277 (Open Web Text)

Max Activating Token Index: 423

Text #17

Max Range: 4.4040. Min Range: -4.4040

Max Act: 4.2223. Min Act: -0.1700

Data Index: 3329596 (Open Web Text)

Max Activating Token Index: 766

Text #18

Max Range: 4.4040. Min Range: -4.4040

Max Act: 4.2143. Min Act: -0.1700

Data Index: 433062 (Open Web Text)

Max Activating Token Index: 598

Text #19

Max Range: 4.4040. Min Range: -4.4040

Max Act: 4.2065. Min Act: -0.1700

Data Index: 979866 (Open Web Text)

Max Activating Token Index: 950