Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 754 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2877. Min Range: -7.2877
Max Act: 7.2877. Min Act: -0.1700
Data Index: 1647006 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2877. Min Range: -7.2877
Max Act: 7.0690. Min Act: -0.1700
Data Index: 1424882 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2877. Min Range: -7.2877
Max Act: 7.0377. Min Act: -0.1700
Data Index: 2470115 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2877. Min Range: -7.2877
Max Act: 6.9752. Min Act: -0.1700
Data Index: 7618139 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2877. Min Range: -7.2877
Max Act: 6.9752. Min Act: -0.1700
Data Index: 5079286 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2877. Min Range: -7.2877
Max Act: 6.8190. Min Act: -0.1700
Data Index: 1411759 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2877. Min Range: -7.2877
Max Act: 6.7565. Min Act: -0.1700
Data Index: 8001985 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2877. Min Range: -7.2877
Max Act: 6.7877. Min Act: -0.1700
Data Index: 4810557 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2877. Min Range: -7.2877
Max Act: 6.6627. Min Act: -0.1700
Data Index: 1675733 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2877. Min Range: -7.2877
Max Act: 6.6940. Min Act: -0.1700
Data Index: 5464750 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2877. Min Range: -7.2877
Max Act: 6.6627. Min Act: -0.1700
Data Index: 6411510 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2877. Min Range: -7.2877
Max Act: 6.6002. Min Act: -0.1700
Data Index: 6191155 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2877. Min Range: -7.2877
Max Act: 6.5690. Min Act: -0.1700
Data Index: 4437776 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2877. Min Range: -7.2877
Max Act: 6.5690. Min Act: -0.1700
Data Index: 3220738 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2877. Min Range: -7.2877
Max Act: 6.5690. Min Act: -0.1700
Data Index: 2713825 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2877. Min Range: -7.2877
Max Act: 6.5690. Min Act: -0.1700
Data Index: 3030340 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2877. Min Range: -7.2877
Max Act: 6.5377. Min Act: -0.1700
Data Index: 2220547 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2877. Min Range: -7.2877
Max Act: 6.5690. Min Act: -0.1700
Data Index: 5247729 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2877. Min Range: -7.2877
Max Act: 6.4752. Min Act: -0.1700
Data Index: 4043854 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2877. Min Range: -7.2877
Max Act: 6.4752. Min Act: -0.1700
Data Index: 660899 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19