Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2822 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1788. Min Range: -3.1788
Max Act: 3.1788. Min Act: -0.1700
Data Index: 268542 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1788. Min Range: -3.1788
Max Act: 3.1473. Min Act: -0.1700
Data Index: 6704050 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1788. Min Range: -3.1788
Max Act: 3.0843. Min Act: -0.1700
Data Index: 8427785 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1788. Min Range: -3.1788
Max Act: 3.0843. Min Act: -0.1700
Data Index: 4740698 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1788. Min Range: -3.1788
Max Act: 3.0685. Min Act: -0.1700
Data Index: 8253718 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1788. Min Range: -3.1788
Max Act: 3.0843. Min Act: -0.1700
Data Index: 7651716 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1788. Min Range: -3.1788
Max Act: 3.0212. Min Act: -0.1700
Data Index: 6596522 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1788. Min Range: -3.1788
Max Act: 3.0212. Min Act: -0.1700
Data Index: 7586023 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1788. Min Range: -3.1788
Max Act: 3.0054. Min Act: -0.1700
Data Index: 4980946 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1788. Min Range: -3.1788
Max Act: 3.0212. Min Act: -0.1700
Data Index: 4582614 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1788. Min Range: -3.1788
Max Act: 3.0054. Min Act: -0.1700
Data Index: 127167 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1788. Min Range: -3.1788
Max Act: 2.9896. Min Act: -0.1700
Data Index: 4740697 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1788. Min Range: -3.1788
Max Act: 2.9896. Min Act: -0.1700
Data Index: 892631 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1788. Min Range: -3.1788
Max Act: 2.9738. Min Act: -0.1700
Data Index: 8732787 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1788. Min Range: -3.1788
Max Act: 2.9896. Min Act: -0.1700
Data Index: 7022412 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1788. Min Range: -3.1788
Max Act: 2.9579. Min Act: -0.1700
Data Index: 5985567 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1788. Min Range: -3.1788
Max Act: 2.9579. Min Act: -0.1700
Data Index: 2962532 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1788. Min Range: -3.1788
Max Act: 2.9579. Min Act: -0.1700
Data Index: 3358097 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1788. Min Range: -3.1788
Max Act: 2.9421. Min Act: -0.1700
Data Index: 1699352 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1788. Min Range: -3.1788
Max Act: 2.9421. Min Act: -0.1700
Data Index: 3014222 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19