Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6068 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.8663. Min Act: -0.1700
Data Index: 4702124 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.8663. Min Act: -0.1700
Data Index: 516978 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.8350. Min Act: -0.1700
Data Index: 1702247 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.8038. Min Act: -0.1700
Data Index: 1863264 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.8038. Min Act: -0.1700
Data Index: 2326249 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.8038. Min Act: -0.1700
Data Index: 169645 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7725. Min Act: -0.1700
Data Index: 6280619 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7725. Min Act: -0.1700
Data Index: 3598602 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7725. Min Act: -0.1700
Data Index: 6915279 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7725. Min Act: -0.1700
Data Index: 3606450 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7725. Min Act: -0.1700
Data Index: 4259117 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7413. Min Act: -0.1700
Data Index: 6990467 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7413. Min Act: -0.1700
Data Index: 8176824 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7413. Min Act: -0.1700
Data Index: 7832610 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7413. Min Act: -0.1700
Data Index: 1232912 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7413. Min Act: -0.1700
Data Index: 7457366 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7413. Min Act: -0.1700
Data Index: 3233460 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7413. Min Act: -0.1700
Data Index: 4222487 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7413. Min Act: -0.1700
Data Index: 2572942 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8663. Min Range: -4.8663
Max Act: 4.7100. Min Act: -0.1700
Data Index: 6684180 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19