Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5816 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.3576. Min Act: -0.1700
Data Index: 6219178 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.3576. Min Act: -0.1700
Data Index: 2048887 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.3576. Min Act: -0.1700
Data Index: 7435993 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.3264. Min Act: -0.1700
Data Index: 1981563 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.2951. Min Act: -0.1699
Data Index: 3399522 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.2639. Min Act: -0.1700
Data Index: 2759746 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.2639. Min Act: -0.1700
Data Index: 6626232 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.2639. Min Act: -0.1700
Data Index: 7156932 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.2639. Min Act: -0.1700
Data Index: 5553147 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.2639. Min Act: -0.1700
Data Index: 5223211 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.2639. Min Act: -0.1700
Data Index: 619549 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.2326. Min Act: -0.1700
Data Index: 5570752 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.2326. Min Act: -0.1700
Data Index: 3595745 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.2639. Min Act: -0.1700
Data Index: 2567644 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.2326. Min Act: -0.1700
Data Index: 361571 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.2326. Min Act: -0.1700
Data Index: 1611556 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.2014. Min Act: -0.1700
Data Index: 2467361 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.2326. Min Act: -0.1700
Data Index: 5223213 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.2014. Min Act: -0.1697
Data Index: 2367541 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3576. Min Range: -6.3576
Max Act: 6.2014. Min Act: -0.1700
Data Index: 4834203 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19