Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3831 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0926. Min Range: -4.0926
Max Act: 4.0926. Min Act: -0.1700
Data Index: 2477117 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.9676. Min Act: -0.1700
Data Index: 8709217 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.8738. Min Act: -0.1700
Data Index: 7615786 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.8582. Min Act: -0.1700
Data Index: 5334977 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.8425. Min Act: -0.1700
Data Index: 5025451 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.8269. Min Act: -0.1700
Data Index: 5989050 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.8269. Min Act: -0.1700
Data Index: 5025439 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.8269. Min Act: -0.1700
Data Index: 5019914 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7956. Min Act: -0.1700
Data Index: 8439295 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7487. Min Act: -0.1700
Data Index: 1958750 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7800. Min Act: -0.1700
Data Index: 1690043 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7487. Min Act: -0.1700
Data Index: 2467487 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7643. Min Act: -0.1700
Data Index: 7381121 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7487. Min Act: -0.1700
Data Index: 7771882 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7487. Min Act: -0.1700
Data Index: 3606274 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7174. Min Act: -0.1700
Data Index: 5529066 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7174. Min Act: -0.1700
Data Index: 7553213 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7018. Min Act: -0.1700
Data Index: 3477186 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7174. Min Act: -0.1700
Data Index: 7632398 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0926. Min Range: -4.0926
Max Act: 3.7018. Min Act: -0.1700
Data Index: 2871605 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19