Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1820 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3556. Min Range: -4.3556
Max Act: 4.3556. Min Act: -0.1700
Data Index: 6864935 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3556. Min Range: -4.3556
Max Act: 4.3244. Min Act: -0.1700
Data Index: 6285438 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3556. Min Range: -4.3556
Max Act: 4.1056. Min Act: -0.1700
Data Index: 7214022 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3556. Min Range: -4.3556
Max Act: 4.0743. Min Act: -0.1700
Data Index: 8653647 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3556. Min Range: -4.3556
Max Act: 4.0118. Min Act: -0.1700
Data Index: 7113624 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3556. Min Range: -4.3556
Max Act: 3.9806. Min Act: -0.1700
Data Index: 1273823 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3556. Min Range: -4.3556
Max Act: 3.9806. Min Act: -0.1700
Data Index: 7729748 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3556. Min Range: -4.3556
Max Act: 3.9493. Min Act: -0.1700
Data Index: 7675843 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3556. Min Range: -4.3556
Max Act: 3.9493. Min Act: -0.1700
Data Index: 1962812 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3556. Min Range: -4.3556
Max Act: 3.9180. Min Act: -0.1700
Data Index: 5404820 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3556. Min Range: -4.3556
Max Act: 3.9180. Min Act: -0.1700
Data Index: 1273194 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3556. Min Range: -4.3556
Max Act: 3.9180. Min Act: -0.1700
Data Index: 4598466 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3556. Min Range: -4.3556
Max Act: 3.9180. Min Act: -0.1700
Data Index: 7113628 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3556. Min Range: -4.3556
Max Act: 3.9180. Min Act: -0.1700
Data Index: 3928079 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3556. Min Range: -4.3556
Max Act: 3.9180. Min Act: -0.1700
Data Index: 2136535 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3556. Min Range: -4.3556
Max Act: 3.9180. Min Act: -0.1700
Data Index: 8812733 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3556. Min Range: -4.3556
Max Act: 3.8868. Min Act: -0.1700
Data Index: 8653646 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3556. Min Range: -4.3556
Max Act: 3.8868. Min Act: -0.1700
Data Index: 5139236 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3556. Min Range: -4.3556
Max Act: 3.9180. Min Act: -0.1700
Data Index: 173779 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3556. Min Range: -4.3556
Max Act: 3.8868. Min Act: -0.1700
Data Index: 1127169 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19