Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4505 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.9208. Min Act: -0.1700
Data Index: 1157659 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.8895. Min Act: -0.1700
Data Index: 511197 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.8895. Min Act: -0.1700
Data Index: 132202 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.8270. Min Act: -0.1700
Data Index: 6054027 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.7645. Min Act: -0.1700
Data Index: 7043183 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.6708. Min Act: -0.1700
Data Index: 87005 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.6708. Min Act: -0.1700
Data Index: 3186769 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.6708. Min Act: -0.1700
Data Index: 5768636 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.6395. Min Act: -0.1700
Data Index: 3017670 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.6395. Min Act: -0.1700
Data Index: 7876639 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.6395. Min Act: -0.1700
Data Index: 4653572 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.6708. Min Act: -0.1700
Data Index: 3418419 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.6395. Min Act: -0.1700
Data Index: 1395553 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.6083. Min Act: -0.1700
Data Index: 3782109 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.5770. Min Act: -0.1700
Data Index: 8492894 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.5458. Min Act: -0.1700
Data Index: 5190557 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.5770. Min Act: -0.1700
Data Index: 4109867 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.5770. Min Act: -0.1700
Data Index: 979270 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.5145. Min Act: -0.1700
Data Index: 6310015 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9208. Min Range: -5.9208
Max Act: 5.5458. Min Act: -0.1700
Data Index: 7191110 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19