Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5617 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1405. Min Range: -6.1405
Max Act: 6.1405. Min Act: -0.1700
Data Index: 1239623 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1405. Min Range: -6.1405
Max Act: 5.9530. Min Act: -0.1700
Data Index: 5741188 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1405. Min Range: -6.1405
Max Act: 5.9217. Min Act: -0.1700
Data Index: 3989284 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1405. Min Range: -6.1405
Max Act: 5.9217. Min Act: -0.1700
Data Index: 5410156 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1405. Min Range: -6.1405
Max Act: 5.8905. Min Act: -0.1700
Data Index: 21750 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1405. Min Range: -6.1405
Max Act: 5.8905. Min Act: -0.1700
Data Index: 3989283 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1405. Min Range: -6.1405
Max Act: 5.8905. Min Act: -0.1700
Data Index: 7786705 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1405. Min Range: -6.1405
Max Act: 5.8280. Min Act: -0.1700
Data Index: 6415281 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1405. Min Range: -6.1405
Max Act: 5.8280. Min Act: -0.1700
Data Index: 21751 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1405. Min Range: -6.1405
Max Act: 5.8592. Min Act: -0.1700
Data Index: 4960642 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1405. Min Range: -6.1405
Max Act: 5.7967. Min Act: -0.1700
Data Index: 6754180 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1405. Min Range: -6.1405
Max Act: 5.7967. Min Act: -0.1700
Data Index: 3801570 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1405. Min Range: -6.1405
Max Act: 5.7967. Min Act: -0.1700
Data Index: 4850435 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1405. Min Range: -6.1405
Max Act: 5.7655. Min Act: -0.1700
Data Index: 289042 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1405. Min Range: -6.1405
Max Act: 5.7342. Min Act: -0.1700
Data Index: 3991311 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1405. Min Range: -6.1405
Max Act: 5.7342. Min Act: -0.1700
Data Index: 6377686 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1405. Min Range: -6.1405
Max Act: 5.7967. Min Act: -0.1700
Data Index: 7922515 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1405. Min Range: -6.1405
Max Act: 5.7655. Min Act: -0.1700
Data Index: 5237052 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1405. Min Range: -6.1405
Max Act: 5.7342. Min Act: -0.1700
Data Index: 3638333 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1405. Min Range: -6.1405
Max Act: 5.7342. Min Act: -0.1700
Data Index: 7822692 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19