Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1694. Min Range: -7.1694
Max Act: 7.1694. Min Act: -0.1700
Data Index: 1593257 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1694. Min Range: -7.1694
Max Act: 7.1694. Min Act: -0.1700
Data Index: 5945194 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1694. Min Range: -7.1694
Max Act: 7.1069. Min Act: -0.1700
Data Index: 3591514 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1694. Min Range: -7.1694
Max Act: 6.9819. Min Act: -0.1700
Data Index: 4005508 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1694. Min Range: -7.1694
Max Act: 7.0132. Min Act: -0.1700
Data Index: 7179309 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1694. Min Range: -7.1694
Max Act: 6.9507. Min Act: -0.1700
Data Index: 6563349 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1694. Min Range: -7.1694
Max Act: 6.9507. Min Act: -0.1700
Data Index: 6800619 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1694. Min Range: -7.1694
Max Act: 6.9194. Min Act: -0.1700
Data Index: 1726468 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1694. Min Range: -7.1694
Max Act: 6.8569. Min Act: -0.1700
Data Index: 1555442 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1694. Min Range: -7.1694
Max Act: 6.8569. Min Act: -0.1700
Data Index: 7719968 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1694. Min Range: -7.1694
Max Act: 6.8569. Min Act: -0.1700
Data Index: 1948867 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1694. Min Range: -7.1694
Max Act: 6.8569. Min Act: -0.1700
Data Index: 4040532 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1694. Min Range: -7.1694
Max Act: 6.8569. Min Act: -0.1700
Data Index: 674536 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1694. Min Range: -7.1694
Max Act: 6.7944. Min Act: -0.1700
Data Index: 1354104 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1694. Min Range: -7.1694
Max Act: 6.8257. Min Act: -0.1700
Data Index: 7545208 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1694. Min Range: -7.1694
Max Act: 6.7632. Min Act: -0.1700
Data Index: 2489028 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1694. Min Range: -7.1694
Max Act: 6.7944. Min Act: -0.1700
Data Index: 1638022 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1694. Min Range: -7.1694
Max Act: 6.7944. Min Act: -0.1700
Data Index: 6187725 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1694. Min Range: -7.1694
Max Act: 6.7319. Min Act: -0.1700
Data Index: 185131 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1694. Min Range: -7.1694
Max Act: 6.7632. Min Act: -0.1700
Data Index: 5401404 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19