Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4756 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4872. Min Range: -7.4872
Max Act: 7.4872. Min Act: -0.1700
Data Index: 3562077 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4872. Min Range: -7.4872
Max Act: 7.3935. Min Act: -0.1700
Data Index: 5573343 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4872. Min Range: -7.4872
Max Act: 7.2685. Min Act: -0.1700
Data Index: 7900693 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4872. Min Range: -7.4872
Max Act: 7.2372. Min Act: -0.1700
Data Index: 8669757 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4872. Min Range: -7.4872
Max Act: 7.2060. Min Act: -0.1700
Data Index: 7611490 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4872. Min Range: -7.4872
Max Act: 7.1747. Min Act: -0.1700
Data Index: 1424893 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4872. Min Range: -7.4872
Max Act: 7.1122. Min Act: -0.1700
Data Index: 4095888 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4872. Min Range: -7.4872
Max Act: 7.1122. Min Act: -0.1700
Data Index: 2998671 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4872. Min Range: -7.4872
Max Act: 7.0810. Min Act: -0.1700
Data Index: 8251307 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4872. Min Range: -7.4872
Max Act: 7.0497. Min Act: -0.1700
Data Index: 8550964 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4872. Min Range: -7.4872
Max Act: 7.0497. Min Act: -0.1700
Data Index: 7900690 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4872. Min Range: -7.4872
Max Act: 6.9247. Min Act: -0.1700
Data Index: 7379776 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4872. Min Range: -7.4872
Max Act: 6.9560. Min Act: -0.1700
Data Index: 8642816 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4872. Min Range: -7.4872
Max Act: 6.9247. Min Act: -0.1700
Data Index: 2074687 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4872. Min Range: -7.4872
Max Act: 6.8935. Min Act: -0.1700
Data Index: 8642815 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4872. Min Range: -7.4872
Max Act: 6.8935. Min Act: -0.1700
Data Index: 7190537 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4872. Min Range: -7.4872
Max Act: 6.8935. Min Act: -0.1700
Data Index: 1242152 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4872. Min Range: -7.4872
Max Act: 6.7997. Min Act: -0.1700
Data Index: 215420 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4872. Min Range: -7.4872
Max Act: 6.8310. Min Act: -0.1700
Data Index: 7379780 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4872. Min Range: -7.4872
Max Act: 6.8310. Min Act: -0.1700
Data Index: 1996372 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19