Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4768 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4049. Min Range: -4.4049
Max Act: 4.4049. Min Act: -0.1700
Data Index: 1181123 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4049. Min Range: -4.4049
Max Act: 4.2174. Min Act: -0.1700
Data Index: 3971441 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4049. Min Range: -4.4049
Max Act: 4.0924. Min Act: -0.1700
Data Index: 1252853 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4049. Min Range: -4.4049
Max Act: 4.0298. Min Act: -0.1700
Data Index: 4235015 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4049. Min Range: -4.4049
Max Act: 4.0298. Min Act: -0.1700
Data Index: 941675 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4049. Min Range: -4.4049
Max Act: 3.9986. Min Act: -0.1700
Data Index: 5194411 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4049. Min Range: -4.4049
Max Act: 3.9673. Min Act: -0.1700
Data Index: 350477 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4049. Min Range: -4.4049
Max Act: 3.9986. Min Act: -0.1700
Data Index: 4416117 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4049. Min Range: -4.4049
Max Act: 3.9361. Min Act: -0.1700
Data Index: 6943066 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4049. Min Range: -4.4049
Max Act: 3.9673. Min Act: -0.1700
Data Index: 6493684 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4049. Min Range: -4.4049
Max Act: 3.9361. Min Act: -0.1700
Data Index: 3359017 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4049. Min Range: -4.4049
Max Act: 3.9361. Min Act: -0.1700
Data Index: 4135847 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4049. Min Range: -4.4049
Max Act: 3.9361. Min Act: -0.1700
Data Index: 643722 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4049. Min Range: -4.4049
Max Act: 3.9048. Min Act: -0.1700
Data Index: 4013902 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4049. Min Range: -4.4049
Max Act: 3.9048. Min Act: -0.1700
Data Index: 1596620 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4049. Min Range: -4.4049
Max Act: 3.9048. Min Act: -0.1700
Data Index: 7482864 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4049. Min Range: -4.4049
Max Act: 3.8735. Min Act: -0.1700
Data Index: 7158025 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4049. Min Range: -4.4049
Max Act: 3.8735. Min Act: -0.1700
Data Index: 5721702 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4049. Min Range: -4.4049
Max Act: 3.8423. Min Act: -0.1700
Data Index: 3306619 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4049. Min Range: -4.4049
Max Act: 3.8423. Min Act: -0.1700
Data Index: 6478030 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19