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

Dataset: Open Web Text

Neuron 1503 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: 5.5939. Min Range: -5.5939

Max Act: 5.5939. Min Act: -0.1700

Data Index: 1245335 (Open Web Text)

Max Activating Token Index: 952

Text #1

Max Range: 5.5939. Min Range: -5.5939

Max Act: 5.5230. Min Act: -0.1700

Data Index: 3694815 (Open Web Text)

Max Activating Token Index: 496

Text #2

Max Range: 5.5939. Min Range: -5.5939

Max Act: 5.5100. Min Act: -0.1700

Data Index: 6777571 (Open Web Text)

Max Activating Token Index: 545

Text #3

Max Range: 5.5939. Min Range: -5.5939

Max Act: 5.4725. Min Act: -0.1700

Data Index: 1245333 (Open Web Text)

Max Activating Token Index: 397

Text #4

Max Range: 5.5939. Min Range: -5.5939

Max Act: 5.4513. Min Act: -0.1700

Data Index: 8758064 (Open Web Text)

Max Activating Token Index: 521

Text #5

Max Range: 5.5939. Min Range: -5.5939

Max Act: 5.4747. Min Act: -0.1700

Data Index: 6777548 (Open Web Text)

Max Activating Token Index: 488

Text #6

Max Range: 5.5939. Min Range: -5.5939

Max Act: 5.4487. Min Act: -0.1700

Data Index: 6720260 (Open Web Text)

Max Activating Token Index: 520

Text #7

Max Range: 5.5939. Min Range: -5.5939

Max Act: 5.3965. Min Act: -0.1700

Data Index: 6720261 (Open Web Text)

Max Activating Token Index: 443

Text #8

Max Range: 5.5939. Min Range: -5.5939

Max Act: 5.4122. Min Act: -0.1700

Data Index: 6583937 (Open Web Text)

Max Activating Token Index: 677

Text #9

Max Range: 5.5939. Min Range: -5.5939

Max Act: 5.4048. Min Act: -0.1700

Data Index: 6720262 (Open Web Text)

Max Activating Token Index: 340

Text #10

Max Range: 5.5939. Min Range: -5.5939

Max Act: 5.3870. Min Act: -0.1700

Data Index: 62511 (Open Web Text)

Max Activating Token Index: 462

Text #11

Max Range: 5.5939. Min Range: -5.5939

Max Act: 5.3719. Min Act: -0.1700

Data Index: 6832274 (Open Web Text)

Max Activating Token Index: 464

Text #12

Max Range: 5.5939. Min Range: -5.5939

Max Act: 5.3596. Min Act: -0.1700

Data Index: 483568 (Open Web Text)

Max Activating Token Index: 478

Text #13

Max Range: 5.5939. Min Range: -5.5939

Max Act: 5.3356. Min Act: -0.1700

Data Index: 1044263 (Open Web Text)

Max Activating Token Index: 335

Text #14

Max Range: 5.5939. Min Range: -5.5939

Max Act: 5.3433. Min Act: -0.1700

Data Index: 5090786 (Open Web Text)

Max Activating Token Index: 588

Text #15

Max Range: 5.5939. Min Range: -5.5939

Max Act: 5.3756. Min Act: -0.1700

Data Index: 151463 (Open Web Text)

Max Activating Token Index: 848

Text #16

Max Range: 5.5939. Min Range: -5.5939

Max Act: 5.3430. Min Act: -0.1700

Data Index: 3292816 (Open Web Text)

Max Activating Token Index: 130

Text #17

Max Range: 5.5939. Min Range: -5.5939

Max Act: 5.3431. Min Act: -0.1700

Data Index: 7366928 (Open Web Text)

Max Activating Token Index: 907

Text #18

Max Range: 5.5939. Min Range: -5.5939

Max Act: 5.3507. Min Act: -0.1700

Data Index: 7864615 (Open Web Text)

Max Activating Token Index: 797

Text #19

Max Range: 5.5939. Min Range: -5.5939

Max Act: 5.3489. Min Act: -0.1700

Data Index: 6584247 (Open Web Text)

Max Activating Token Index: 158