Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5941 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1824. Min Range: -8.1824
Max Act: 8.1824. Min Act: -0.1700
Data Index: 6881535 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1824. Min Range: -8.1824
Max Act: 7.9636. Min Act: -0.1700
Data Index: 3993943 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1824. Min Range: -8.1824
Max Act: 7.7761. Min Act: -0.1700
Data Index: 1027368 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1824. Min Range: -8.1824
Max Act: 7.6199. Min Act: -0.1700
Data Index: 1332142 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1824. Min Range: -8.1824
Max Act: 7.5261. Min Act: -0.1700
Data Index: 2640259 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1824. Min Range: -8.1824
Max Act: 7.4636. Min Act: -0.1700
Data Index: 2309566 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1824. Min Range: -8.1824
Max Act: 7.4636. Min Act: -0.1700
Data Index: 1338517 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1824. Min Range: -8.1824
Max Act: 7.4324. Min Act: -0.1700
Data Index: 6532530 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1824. Min Range: -8.1824
Max Act: 7.3699. Min Act: -0.1700
Data Index: 7521103 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1824. Min Range: -8.1824
Max Act: 7.3386. Min Act: -0.1700
Data Index: 6901588 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1824. Min Range: -8.1824
Max Act: 7.2761. Min Act: -0.1700
Data Index: 4792519 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1824. Min Range: -8.1824
Max Act: 7.2449. Min Act: -0.1700
Data Index: 3150968 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1824. Min Range: -8.1824
Max Act: 7.2449. Min Act: -0.1700
Data Index: 6390735 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1824. Min Range: -8.1824
Max Act: 7.1824. Min Act: -0.1700
Data Index: 958869 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1824. Min Range: -8.1824
Max Act: 7.2136. Min Act: -0.1700
Data Index: 7687852 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1824. Min Range: -8.1824
Max Act: 7.1824. Min Act: -0.1700
Data Index: 7213689 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1824. Min Range: -8.1824
Max Act: 7.2136. Min Act: -0.1700
Data Index: 4107743 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1824. Min Range: -8.1824
Max Act: 7.1511. Min Act: -0.1700
Data Index: 5971628 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1824. Min Range: -8.1824
Max Act: 7.1511. Min Act: -0.1700
Data Index: 6969789 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1824. Min Range: -8.1824
Max Act: 7.1199. Min Act: -0.1700
Data Index: 2126803 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19