Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3534 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.3618. Min Act: -0.1700
Data Index: 7776612 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.2056. Min Act: -0.1700
Data Index: 5786576 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.2056. Min Act: -0.1700
Data Index: 6148222 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.1743. Min Act: -0.1699
Data Index: 76878 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.1431. Min Act: -0.1700
Data Index: 8198015 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.1118. Min Act: -0.1693
Data Index: 5671882 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.0806. Min Act: -0.1700
Data Index: 2965932 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.0806. Min Act: -0.1700
Data Index: 96383 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.0806. Min Act: -0.1700
Data Index: 2904483 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.0806. Min Act: -0.1699
Data Index: 2892053 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.0806. Min Act: -0.1700
Data Index: 392254 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.0806. Min Act: -0.1700
Data Index: 2860811 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.0806. Min Act: -0.1700
Data Index: 2779777 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.0806. Min Act: -0.1697
Data Index: 395977 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.0806. Min Act: -0.1700
Data Index: 2740771 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.0806. Min Act: -0.1700
Data Index: 2108894 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.0806. Min Act: -0.1700
Data Index: 2040533 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.0806. Min Act: -0.1700
Data Index: 2034670 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.0806. Min Act: -0.1700
Data Index: 2034428 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3618. Min Range: -5.3618
Max Act: 5.0806. Min Act: -0.1700
Data Index: 1589073 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19