Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3272 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.8464. Min Act: -0.1700
Data Index: 6575002 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.7839. Min Act: -0.1700
Data Index: 5259691 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.7839. Min Act: -0.1700
Data Index: 1833187 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.7839. Min Act: -0.1700
Data Index: 1658043 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.7527. Min Act: -0.1700
Data Index: 1616585 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.7839. Min Act: -0.1700
Data Index: 6858178 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.6902. Min Act: -0.1700
Data Index: 1616576 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.6902. Min Act: -0.1700
Data Index: 5648557 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.6589. Min Act: -0.1700
Data Index: 8397110 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.6902. Min Act: -0.1700
Data Index: 4720951 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.6589. Min Act: -0.1700
Data Index: 7574594 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.6589. Min Act: -0.1700
Data Index: 6245641 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.6589. Min Act: -0.1700
Data Index: 7186000 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.6589. Min Act: -0.1700
Data Index: 8814771 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.6277. Min Act: -0.1700
Data Index: 632804 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.5964. Min Act: -0.1700
Data Index: 6265401 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.6277. Min Act: -0.1700
Data Index: 7580490 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.5652. Min Act: -0.1700
Data Index: 5471875 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.5964. Min Act: -0.1700
Data Index: 3546794 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8464. Min Range: -4.8464
Max Act: 4.5964. Min Act: -0.1700
Data Index: 3753009 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19