Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5979 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0640. Min Range: -8.0640
Max Act: 8.0640. Min Act: -0.1700
Data Index: 3977246 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0640. Min Range: -8.0640
Max Act: 7.6890. Min Act: -0.1700
Data Index: 3395980 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0640. Min Range: -8.0640
Max Act: 7.6890. Min Act: -0.1700
Data Index: 2172506 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0640. Min Range: -8.0640
Max Act: 7.6265. Min Act: -0.1700
Data Index: 2458670 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0640. Min Range: -8.0640
Max Act: 7.5640. Min Act: -0.1700
Data Index: 7758084 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0640. Min Range: -8.0640
Max Act: 7.5640. Min Act: -0.1700
Data Index: 4516660 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0640. Min Range: -8.0640
Max Act: 7.5015. Min Act: -0.1700
Data Index: 6319359 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0640. Min Range: -8.0640
Max Act: 7.5640. Min Act: -0.1700
Data Index: 4560720 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0640. Min Range: -8.0640
Max Act: 7.5015. Min Act: -0.1700
Data Index: 4083773 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0640. Min Range: -8.0640
Max Act: 7.4390. Min Act: -0.1700
Data Index: 214528 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0640. Min Range: -8.0640
Max Act: 7.4702. Min Act: -0.1700
Data Index: 2767316 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0640. Min Range: -8.0640
Max Act: 7.4390. Min Act: -0.1700
Data Index: 7152238 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0640. Min Range: -8.0640
Max Act: 7.4077. Min Act: -0.1700
Data Index: 3654046 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0640. Min Range: -8.0640
Max Act: 7.4390. Min Act: -0.1700
Data Index: 2064626 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0640. Min Range: -8.0640
Max Act: 7.3765. Min Act: -0.1700
Data Index: 642505 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0640. Min Range: -8.0640
Max Act: 7.3452. Min Act: -0.1700
Data Index: 5948135 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0640. Min Range: -8.0640
Max Act: 7.3765. Min Act: -0.1700
Data Index: 5135882 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0640. Min Range: -8.0640
Max Act: 7.3765. Min Act: -0.1700
Data Index: 1360982 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0640. Min Range: -8.0640
Max Act: 7.3452. Min Act: -0.1700
Data Index: 1893789 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0640. Min Range: -8.0640
Max Act: 7.3452. Min Act: -0.1700
Data Index: 2519942 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19