Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3282 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0541. Min Range: -4.0541
Max Act: 4.0541. Min Act: -0.1700
Data Index: 2477144 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.9291. Min Act: -0.1700
Data Index: 1405317 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.9291. Min Act: -0.1700
Data Index: 8406603 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.8665. Min Act: -0.1700
Data Index: 5114847 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.8353. Min Act: -0.1700
Data Index: 8622215 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.8353. Min Act: -0.1700
Data Index: 7672843 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.8353. Min Act: -0.1700
Data Index: 4263248 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.8040. Min Act: -0.1700
Data Index: 3171655 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.8040. Min Act: -0.1700
Data Index: 3328549 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.8040. Min Act: -0.1700
Data Index: 4933275 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.7727. Min Act: -0.1700
Data Index: 1995753 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.7727. Min Act: -0.1700
Data Index: 536403 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.7727. Min Act: -0.1700
Data Index: 5454887 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.7727. Min Act: -0.1700
Data Index: 6791539 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.7727. Min Act: -0.1700
Data Index: 6341529 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.7414. Min Act: -0.1700
Data Index: 3240884 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.7101. Min Act: -0.1700
Data Index: 5455862 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.7101. Min Act: -0.1700
Data Index: 5945648 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.7101. Min Act: -0.1700
Data Index: 7672842 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0541. Min Range: -4.0541
Max Act: 3.7101. Min Act: -0.1700
Data Index: 6070877 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19