Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3403 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.9806. Min Act: -0.1700
Data Index: 4349531 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.8556. Min Act: -0.1700
Data Index: 6245076 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.8556. Min Act: -0.1700
Data Index: 7590449 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.8243. Min Act: -0.1700
Data Index: 4423843 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.7306. Min Act: -0.1700
Data Index: 8142707 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.7306. Min Act: -0.1700
Data Index: 863773 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6993. Min Act: -0.1700
Data Index: 5182736 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6993. Min Act: -0.1700
Data Index: 6558048 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6993. Min Act: -0.1700
Data Index: 4553521 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6681. Min Act: -0.1700
Data Index: 7733031 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6681. Min Act: -0.1700
Data Index: 2190593 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6681. Min Act: -0.1700
Data Index: 6873175 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6681. Min Act: -0.1700
Data Index: 3691912 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.6368. Min Act: -0.1700
Data Index: 5530120 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.5743. Min Act: -0.1700
Data Index: 2743342 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.5743. Min Act: -0.1700
Data Index: 6102759 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.5431. Min Act: -0.1700
Data Index: 6486848 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.5118. Min Act: -0.1700
Data Index: 2214853 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.5118. Min Act: -0.1700
Data Index: 3342282 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9806. Min Range: -4.9806
Max Act: 4.5118. Min Act: -0.1700
Data Index: 3574172 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19