Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3581 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.6014. Min Act: -0.1700
Data Index: 1589145 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.4764. Min Act: -0.1700
Data Index: 5605293 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.4764. Min Act: -0.1700
Data Index: 6630068 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.4139. Min Act: -0.1700
Data Index: 2792943 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.4139. Min Act: -0.1700
Data Index: 3157785 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.3827. Min Act: -0.1700
Data Index: 4934347 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.3202. Min Act: -0.1700
Data Index: 5830525 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.3202. Min Act: -0.1700
Data Index: 3189652 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.3514. Min Act: -0.1700
Data Index: 7353319 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.3202. Min Act: -0.1700
Data Index: 230101 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.2577. Min Act: -0.1700
Data Index: 7334566 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.2577. Min Act: -0.1700
Data Index: 4454428 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.2577. Min Act: -0.1700
Data Index: 6692505 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.2577. Min Act: -0.1700
Data Index: 8813260 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.2264. Min Act: -0.1700
Data Index: 7602901 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.2264. Min Act: -0.1700
Data Index: 4803209 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.2577. Min Act: -0.1700
Data Index: 5596238 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.2264. Min Act: -0.1700
Data Index: 4753564 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.2264. Min Act: -0.1700
Data Index: 1263107 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6014. Min Range: -5.6014
Max Act: 5.1952. Min Act: -0.1700
Data Index: 4764594 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19