Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1806 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.9688. Min Act: -0.1700
Data Index: 2888792 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.6250. Min Act: -0.1700
Data Index: 5770250 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.6250. Min Act: -0.1700
Data Index: 7693367 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.5938. Min Act: -0.1700
Data Index: 22576 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.5625. Min Act: -0.1700
Data Index: 8564456 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.5000. Min Act: -0.1700
Data Index: 3907815 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.4688. Min Act: -0.1700
Data Index: 4780755 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.4688. Min Act: -0.1700
Data Index: 1232701 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.4688. Min Act: -0.1700
Data Index: 1480020 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.4375. Min Act: -0.1700
Data Index: 3717948 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.3750. Min Act: -0.1700
Data Index: 6132095 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.3750. Min Act: -0.1700
Data Index: 5070290 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.3438. Min Act: -0.1700
Data Index: 822964 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.3438. Min Act: -0.1700
Data Index: 34191 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.3438. Min Act: -0.1700
Data Index: 1007377 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.3438. Min Act: -0.1700
Data Index: 5878382 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.3125. Min Act: -0.1700
Data Index: 5169588 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.3125. Min Act: -0.1700
Data Index: 86463 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.2813. Min Act: -0.1700
Data Index: 3821614 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9688. Min Range: -5.9688
Max Act: 5.2813. Min Act: -0.1700
Data Index: 5903057 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19