Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2751 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.6880. Min Act: -0.1700
Data Index: 1483875 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.6255. Min Act: -0.1700
Data Index: 6418951 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.5630. Min Act: -0.1700
Data Index: 7588434 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.5630. Min Act: -0.1700
Data Index: 8221817 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.5317. Min Act: -0.1700
Data Index: 3227833 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.5005. Min Act: -0.1700
Data Index: 8305850 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.5005. Min Act: -0.1700
Data Index: 2339490 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.5005. Min Act: -0.1700
Data Index: 5028840 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.4692. Min Act: -0.1700
Data Index: 515372 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.4692. Min Act: -0.1700
Data Index: 1944088 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.5005. Min Act: -0.1700
Data Index: 4784066 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.4380. Min Act: -0.1700
Data Index: 145902 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.4380. Min Act: -0.1700
Data Index: 561551 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.4067. Min Act: -0.1700
Data Index: 3484885 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.4067. Min Act: -0.1700
Data Index: 6460367 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.4067. Min Act: -0.1700
Data Index: 1666732 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.4067. Min Act: -0.1700
Data Index: 1184384 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.4067. Min Act: -0.1700
Data Index: 190431 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.4067. Min Act: -0.1700
Data Index: 296725 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6880. Min Range: -4.6880
Max Act: 4.3755. Min Act: -0.1700
Data Index: 6776567 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19