Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3766 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.3910. Min Act: -0.1700
Data Index: 4791006 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.3598. Min Act: -0.1700
Data Index: 7448974 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.2660. Min Act: -0.1700
Data Index: 672429 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.2348. Min Act: -0.1700
Data Index: 1376862 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.1723. Min Act: -0.1700
Data Index: 2093648 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.2035. Min Act: -0.1700
Data Index: 8372333 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.2035. Min Act: -0.1700
Data Index: 3012463 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.1410. Min Act: -0.1700
Data Index: 7459685 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.1723. Min Act: -0.1700
Data Index: 2303535 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.1723. Min Act: -0.1700
Data Index: 2727884 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.1723. Min Act: -0.1700
Data Index: 6813197 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.1723. Min Act: -0.1700
Data Index: 873878 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.1410. Min Act: -0.1700
Data Index: 2031058 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.1410. Min Act: -0.1700
Data Index: 8141206 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.1098. Min Act: -0.1700
Data Index: 655301 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.1410. Min Act: -0.1700
Data Index: 3012464 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.1723. Min Act: -0.1700
Data Index: 6720433 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.1098. Min Act: -0.1700
Data Index: 6585300 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.1098. Min Act: -0.1700
Data Index: 2209344 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3910. Min Range: -5.3910
Max Act: 5.1098. Min Act: -0.1700
Data Index: 4531975 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19