Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4944 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0753. Min Range: -5.0753
Max Act: 5.0753. Min Act: -0.1700
Data Index: 255760 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0753. Min Range: -5.0753
Max Act: 4.7315. Min Act: -0.1700
Data Index: 2835873 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0753. Min Range: -5.0753
Max Act: 4.7315. Min Act: -0.1700
Data Index: 898487 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0753. Min Range: -5.0753
Max Act: 4.7003. Min Act: -0.1700
Data Index: 3560026 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0753. Min Range: -5.0753
Max Act: 4.7003. Min Act: -0.1700
Data Index: 161687 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0753. Min Range: -5.0753
Max Act: 4.6690. Min Act: -0.1700
Data Index: 3565233 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0753. Min Range: -5.0753
Max Act: 4.5753. Min Act: -0.1700
Data Index: 271261 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0753. Min Range: -5.0753
Max Act: 4.6065. Min Act: -0.1700
Data Index: 7986367 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0753. Min Range: -5.0753
Max Act: 4.6065. Min Act: -0.1700
Data Index: 2440944 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0753. Min Range: -5.0753
Max Act: 4.6065. Min Act: -0.1700
Data Index: 3037908 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0753. Min Range: -5.0753
Max Act: 4.6065. Min Act: -0.1700
Data Index: 4903270 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0753. Min Range: -5.0753
Max Act: 4.6065. Min Act: -0.1700
Data Index: 4595418 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0753. Min Range: -5.0753
Max Act: 4.5753. Min Act: -0.1700
Data Index: 1953494 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0753. Min Range: -5.0753
Max Act: 4.5753. Min Act: -0.1700
Data Index: 10770 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0753. Min Range: -5.0753
Max Act: 4.5753. Min Act: -0.1700
Data Index: 5190778 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0753. Min Range: -5.0753
Max Act: 4.5753. Min Act: -0.1700
Data Index: 2175367 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0753. Min Range: -5.0753
Max Act: 4.5753. Min Act: -0.1700
Data Index: 4097864 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0753. Min Range: -5.0753
Max Act: 4.5753. Min Act: -0.1700
Data Index: 5682715 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0753. Min Range: -5.0753
Max Act: 4.5753. Min Act: -0.1700
Data Index: 1479719 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0753. Min Range: -5.0753
Max Act: 4.5753. Min Act: -0.1700
Data Index: 3709610 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19