Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4787 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.4338. Min Act: -0.1700
Data Index: 962122 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.3088. Min Act: -0.1700
Data Index: 7232651 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.2151. Min Act: -0.1700
Data Index: 3745631 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.2151. Min Act: -0.1700
Data Index: 1972469 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.1838. Min Act: -0.1700
Data Index: 6287399 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.1838. Min Act: -0.1700
Data Index: 6913457 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.1525. Min Act: -0.1700
Data Index: 8637465 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.1525. Min Act: -0.1700
Data Index: 8712590 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.1213. Min Act: -0.1700
Data Index: 1923587 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.1213. Min Act: -0.1700
Data Index: 3328376 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.1213. Min Act: -0.1700
Data Index: 7388833 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.1213. Min Act: -0.1700
Data Index: 36394 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.1213. Min Act: -0.1700
Data Index: 6190091 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.1213. Min Act: -0.1700
Data Index: 5439548 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.1525. Min Act: -0.1700
Data Index: 2076606 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.1213. Min Act: -0.1700
Data Index: 5326739 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.0900. Min Act: -0.1700
Data Index: 7126849 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.0900. Min Act: -0.1700
Data Index: 7183080 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.0900. Min Act: -0.1700
Data Index: 4167596 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4338. Min Range: -4.4338
Max Act: 4.1213. Min Act: -0.1700
Data Index: 8471684 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19