Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4631 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.5480. Min Act: -0.1700
Data Index: 3296231 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.5480. Min Act: -0.1700
Data Index: 8715347 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.4855. Min Act: -0.1700
Data Index: 5538390 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.4230. Min Act: -0.1700
Data Index: 6473528 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.4230. Min Act: -0.1699
Data Index: 1115008 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.4542. Min Act: -0.1700
Data Index: 7059872 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.3917. Min Act: -0.1700
Data Index: 2042161 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.3917. Min Act: -0.1700
Data Index: 2213827 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.3917. Min Act: -0.1700
Data Index: 1863774 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.3917. Min Act: -0.1700
Data Index: 5146887 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.3917. Min Act: -0.1700
Data Index: 569670 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.3605. Min Act: -0.1700
Data Index: 7352858 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.3605. Min Act: -0.1700
Data Index: 5716017 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.3605. Min Act: -0.1700
Data Index: 1858130 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.3605. Min Act: -0.1700
Data Index: 7345241 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.3605. Min Act: -0.1699
Data Index: 1049574 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.3605. Min Act: -0.1700
Data Index: 856 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.3605. Min Act: -0.1699
Data Index: 3594799 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.3605. Min Act: -0.1700
Data Index: 1227649 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5480. Min Range: -5.5480
Max Act: 5.3605. Min Act: -0.1700
Data Index: 6864850 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19