Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5765 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.4798. Min Act: -0.1700
Data Index: 7170828 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3861. Min Act: -0.1700
Data Index: 1734964 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3548. Min Act: -0.1700
Data Index: 6536562 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.3236. Min Act: -0.1700
Data Index: 4897029 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2923. Min Act: -0.1700
Data Index: 1869951 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2923. Min Act: -0.1700
Data Index: 5426649 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2923. Min Act: -0.1700
Data Index: 2550693 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2611. Min Act: -0.1700
Data Index: 4872981 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2611. Min Act: -0.1700
Data Index: 5199248 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2611. Min Act: -0.1700
Data Index: 2907711 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2611. Min Act: -0.1700
Data Index: 6655512 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2611. Min Act: -0.1700
Data Index: 666794 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2298. Min Act: -0.1700
Data Index: 6846964 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2298. Min Act: -0.1700
Data Index: 1829784 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2298. Min Act: -0.1700
Data Index: 2339734 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.2298. Min Act: -0.1700
Data Index: 450638 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1986. Min Act: -0.1700
Data Index: 5139636 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1986. Min Act: -0.1700
Data Index: 1847310 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1986. Min Act: -0.1700
Data Index: 1454199 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4798. Min Range: -5.4798
Max Act: 5.1986. Min Act: -0.1700
Data Index: 450637 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19