Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3038 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.6200. Min Act: -0.1700
Data Index: 4749020 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.5888. Min Act: -0.1700
Data Index: 2709092 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.4950. Min Act: -0.1700
Data Index: 3663744 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.4950. Min Act: -0.1700
Data Index: 2032808 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.4950. Min Act: -0.1700
Data Index: 8811037 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.4638. Min Act: -0.1700
Data Index: 1948580 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.4950. Min Act: -0.1700
Data Index: 135780 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.4325. Min Act: -0.1700
Data Index: 1876269 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.4325. Min Act: -0.1700
Data Index: 6239477 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.4013. Min Act: -0.1700
Data Index: 7968011 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.3700. Min Act: -0.1700
Data Index: 5368808 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.3700. Min Act: -0.1700
Data Index: 6135867 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.3700. Min Act: -0.1700
Data Index: 4389706 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.3700. Min Act: -0.1700
Data Index: 5521225 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.3700. Min Act: -0.1700
Data Index: 1554829 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.3700. Min Act: -0.1700
Data Index: 6734130 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.3700. Min Act: -0.1699
Data Index: 1739007 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.3700. Min Act: -0.1700
Data Index: 3715079 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.3700. Min Act: -0.1700
Data Index: 1044009 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6200. Min Range: -5.6200
Max Act: 5.3388. Min Act: -0.1700
Data Index: 4335665 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19