Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3268 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0551. Min Range: -5.0551
Max Act: 5.0551. Min Act: -0.1700
Data Index: 1935454 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0551. Min Range: -5.0551
Max Act: 4.9926. Min Act: -0.1700
Data Index: 1023392 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0551. Min Range: -5.0551
Max Act: 4.9926. Min Act: -0.1700
Data Index: 7265960 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0551. Min Range: -5.0551
Max Act: 4.9614. Min Act: -0.1700
Data Index: 1788649 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0551. Min Range: -5.0551
Max Act: 4.9614. Min Act: -0.1700
Data Index: 5397115 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0551. Min Range: -5.0551
Max Act: 4.9301. Min Act: -0.1700
Data Index: 4723369 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0551. Min Range: -5.0551
Max Act: 4.8989. Min Act: -0.1700
Data Index: 4365526 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0551. Min Range: -5.0551
Max Act: 4.8989. Min Act: -0.1700
Data Index: 284371 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0551. Min Range: -5.0551
Max Act: 4.9301. Min Act: -0.1700
Data Index: 8185053 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0551. Min Range: -5.0551
Max Act: 4.8989. Min Act: -0.1700
Data Index: 3124862 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0551. Min Range: -5.0551
Max Act: 4.8989. Min Act: -0.1700
Data Index: 7509476 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0551. Min Range: -5.0551
Max Act: 4.8989. Min Act: -0.1700
Data Index: 6124113 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0551. Min Range: -5.0551
Max Act: 4.8989. Min Act: -0.1700
Data Index: 1488718 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0551. Min Range: -5.0551
Max Act: 4.8676. Min Act: -0.1700
Data Index: 7189641 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0551. Min Range: -5.0551
Max Act: 4.8676. Min Act: -0.1700
Data Index: 8210558 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0551. Min Range: -5.0551
Max Act: 4.8676. Min Act: -0.1700
Data Index: 2749916 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0551. Min Range: -5.0551
Max Act: 4.8676. Min Act: -0.1700
Data Index: 2931223 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0551. Min Range: -5.0551
Max Act: 4.8364. Min Act: -0.1699
Data Index: 4466278 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0551. Min Range: -5.0551
Max Act: 4.8364. Min Act: -0.1700
Data Index: 4186214 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0551. Min Range: -5.0551
Max Act: 4.8364. Min Act: -0.1700
Data Index: 2808033 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19