Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1671 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2908. Min Range: -7.2908
Max Act: 7.2908. Min Act: -0.1700
Data Index: 5709117 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2908. Min Range: -7.2908
Max Act: 7.1033. Min Act: -0.1700
Data Index: 6903284 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2908. Min Range: -7.2908
Max Act: 7.1033. Min Act: -0.1700
Data Index: 5170560 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2908. Min Range: -7.2908
Max Act: 7.0408. Min Act: -0.1700
Data Index: 1718632 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2908. Min Range: -7.2908
Max Act: 6.9783. Min Act: -0.1700
Data Index: 7152684 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2908. Min Range: -7.2908
Max Act: 6.9783. Min Act: -0.1700
Data Index: 8406528 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2908. Min Range: -7.2908
Max Act: 6.9471. Min Act: -0.1700
Data Index: 5392068 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2908. Min Range: -7.2908
Max Act: 6.8533. Min Act: -0.1700
Data Index: 5363464 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2908. Min Range: -7.2908
Max Act: 6.8533. Min Act: -0.1700
Data Index: 4325630 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2908. Min Range: -7.2908
Max Act: 6.7596. Min Act: -0.1700
Data Index: 1096511 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2908. Min Range: -7.2908
Max Act: 6.7283. Min Act: -0.1700
Data Index: 5834788 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2908. Min Range: -7.2908
Max Act: 6.6971. Min Act: -0.1700
Data Index: 406690 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2908. Min Range: -7.2908
Max Act: 6.6971. Min Act: -0.1700
Data Index: 6172643 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2908. Min Range: -7.2908
Max Act: 6.6971. Min Act: -0.1700
Data Index: 5328171 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2908. Min Range: -7.2908
Max Act: 6.6658. Min Act: -0.1700
Data Index: 2654914 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2908. Min Range: -7.2908
Max Act: 6.6658. Min Act: -0.1700
Data Index: 6828054 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2908. Min Range: -7.2908
Max Act: 6.6971. Min Act: -0.1700
Data Index: 6538100 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2908. Min Range: -7.2908
Max Act: 6.6346. Min Act: -0.1700
Data Index: 1217331 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2908. Min Range: -7.2908
Max Act: 6.6346. Min Act: -0.1700
Data Index: 4763968 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2908. Min Range: -7.2908
Max Act: 6.6346. Min Act: -0.1700
Data Index: 2112428 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19