Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3228 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.8865. Min Act: -0.1700
Data Index: 938995 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.8865. Min Act: -0.1700
Data Index: 8521828 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.8552. Min Act: -0.1700
Data Index: 3956501 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.7771. Min Act: -0.1700
Data Index: 584260 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.7771. Min Act: -0.1700
Data Index: 8415062 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.7458. Min Act: -0.1700
Data Index: 792545 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.7458. Min Act: -0.1700
Data Index: 3968331 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.6988. Min Act: -0.1700
Data Index: 4193501 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.6676. Min Act: -0.1700
Data Index: 7627838 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.6676. Min Act: -0.1700
Data Index: 2208201 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.6832. Min Act: -0.1700
Data Index: 6971871 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.6676. Min Act: -0.1700
Data Index: 8125201 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.6832. Min Act: -0.1700
Data Index: 8413567 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.6519. Min Act: -0.1700
Data Index: 7625676 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.6363. Min Act: -0.1700
Data Index: 6233308 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.6676. Min Act: -0.1700
Data Index: 6217623 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.6519. Min Act: -0.1700
Data Index: 6224146 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.6363. Min Act: -0.1700
Data Index: 3477363 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.6363. Min Act: -0.1700
Data Index: 8644299 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8865. Min Range: -3.8865
Max Act: 3.6206. Min Act: -0.1700
Data Index: 353263 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19