Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3735 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3093. Min Range: -9.3093
Max Act: 9.3093. Min Act: -0.1700
Data Index: 4782889 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3093. Min Range: -9.3093
Max Act: 9.0593. Min Act: -0.1700
Data Index: 5243356 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3093. Min Range: -9.3093
Max Act: 9.0593. Min Act: -0.1700
Data Index: 1771006 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3093. Min Range: -9.3093
Max Act: 8.9968. Min Act: -0.1700
Data Index: 4277941 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3093. Min Range: -9.3093
Max Act: 8.9343. Min Act: -0.1700
Data Index: 4296897 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3093. Min Range: -9.3093
Max Act: 8.9343. Min Act: -0.1700
Data Index: 8402908 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3093. Min Range: -9.3093
Max Act: 8.8718. Min Act: -0.1700
Data Index: 7094934 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3093. Min Range: -9.3093
Max Act: 8.8718. Min Act: -0.1700
Data Index: 2974601 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3093. Min Range: -9.3093
Max Act: 8.8718. Min Act: -0.1700
Data Index: 4595501 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3093. Min Range: -9.3093
Max Act: 8.9343. Min Act: -0.1700
Data Index: 208773 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3093. Min Range: -9.3093
Max Act: 8.8093. Min Act: -0.1700
Data Index: 7623662 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3093. Min Range: -9.3093
Max Act: 8.7468. Min Act: -0.1700
Data Index: 3395679 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3093. Min Range: -9.3093
Max Act: 8.8093. Min Act: -0.1700
Data Index: 4682971 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3093. Min Range: -9.3093
Max Act: 8.8093. Min Act: -0.1700
Data Index: 109421 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3093. Min Range: -9.3093
Max Act: 8.8093. Min Act: -0.1700
Data Index: 7550821 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3093. Min Range: -9.3093
Max Act: 8.8093. Min Act: -0.1700
Data Index: 1992936 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3093. Min Range: -9.3093
Max Act: 8.7468. Min Act: -0.1700
Data Index: 313800 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3093. Min Range: -9.3093
Max Act: 8.7468. Min Act: -0.1700
Data Index: 1285194 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3093. Min Range: -9.3093
Max Act: 8.7468. Min Act: -0.1700
Data Index: 2053252 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3093. Min Range: -9.3093
Max Act: 8.7468. Min Act: -0.1700
Data Index: 4836051 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19