Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1222 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1978. Min Range: -5.1978
Max Act: 5.1978. Min Act: -0.1700
Data Index: 6964115 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1978. Min Range: -5.1978
Max Act: 5.1666. Min Act: -0.1700
Data Index: 6964114 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1978. Min Range: -5.1978
Max Act: 5.1353. Min Act: -0.1700
Data Index: 3756614 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1978. Min Range: -5.1978
Max Act: 5.1041. Min Act: -0.1700
Data Index: 5880833 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1978. Min Range: -5.1978
Max Act: 5.0728. Min Act: -0.1700
Data Index: 219660 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1978. Min Range: -5.1978
Max Act: 5.0416. Min Act: -0.1700
Data Index: 6823997 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1978. Min Range: -5.1978
Max Act: 5.0416. Min Act: -0.1700
Data Index: 5290146 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1978. Min Range: -5.1978
Max Act: 5.0103. Min Act: -0.1700
Data Index: 6458815 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1978. Min Range: -5.1978
Max Act: 4.9791. Min Act: -0.1700
Data Index: 4484589 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1978. Min Range: -5.1978
Max Act: 4.9478. Min Act: -0.1700
Data Index: 4998550 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1978. Min Range: -5.1978
Max Act: 4.9478. Min Act: -0.1700
Data Index: 3677097 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1978. Min Range: -5.1978
Max Act: 4.9478. Min Act: -0.1700
Data Index: 4676564 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1978. Min Range: -5.1978
Max Act: 4.9166. Min Act: -0.1700
Data Index: 1978271 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1978. Min Range: -5.1978
Max Act: 4.9166. Min Act: -0.1700
Data Index: 4008197 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1978. Min Range: -5.1978
Max Act: 4.9478. Min Act: -0.1700
Data Index: 3368675 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1978. Min Range: -5.1978
Max Act: 4.9166. Min Act: -0.1700
Data Index: 8687146 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1978. Min Range: -5.1978
Max Act: 4.9166. Min Act: -0.1700
Data Index: 5899755 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1978. Min Range: -5.1978
Max Act: 4.9166. Min Act: -0.1700
Data Index: 816914 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1978. Min Range: -5.1978
Max Act: 4.8853. Min Act: -0.1700
Data Index: 3272200 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1978. Min Range: -5.1978
Max Act: 4.8853. Min Act: -0.1700
Data Index: 3966401 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19