Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5199 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3317. Min Range: -6.3317
Max Act: 6.3317. Min Act: -0.1700
Data Index: 6674905 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3317. Min Range: -6.3317
Max Act: 6.2692. Min Act: -0.1700
Data Index: 3648971 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3317. Min Range: -6.3317
Max Act: 6.1129. Min Act: -0.1700
Data Index: 6981326 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3317. Min Range: -6.3317
Max Act: 6.0192. Min Act: -0.1700
Data Index: 2220852 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3317. Min Range: -6.3317
Max Act: 5.9879. Min Act: -0.1700
Data Index: 66642 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3317. Min Range: -6.3317
Max Act: 5.9567. Min Act: -0.1700
Data Index: 3998448 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3317. Min Range: -6.3317
Max Act: 5.9254. Min Act: -0.1700
Data Index: 2625229 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3317. Min Range: -6.3317
Max Act: 5.8942. Min Act: -0.1700
Data Index: 3000939 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3317. Min Range: -6.3317
Max Act: 5.8942. Min Act: -0.1700
Data Index: 4054766 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3317. Min Range: -6.3317
Max Act: 5.8629. Min Act: -0.1700
Data Index: 998384 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3317. Min Range: -6.3317
Max Act: 5.8629. Min Act: -0.1700
Data Index: 3678525 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3317. Min Range: -6.3317
Max Act: 5.8317. Min Act: -0.1700
Data Index: 4007173 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3317. Min Range: -6.3317
Max Act: 5.8317. Min Act: -0.1700
Data Index: 2364092 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3317. Min Range: -6.3317
Max Act: 5.8317. Min Act: -0.1700
Data Index: 4230538 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3317. Min Range: -6.3317
Max Act: 5.8317. Min Act: -0.1700
Data Index: 1600683 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3317. Min Range: -6.3317
Max Act: 5.8004. Min Act: -0.1700
Data Index: 6937365 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3317. Min Range: -6.3317
Max Act: 5.8004. Min Act: -0.1700
Data Index: 6614883 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3317. Min Range: -6.3317
Max Act: 5.8004. Min Act: -0.1700
Data Index: 8800681 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3317. Min Range: -6.3317
Max Act: 5.8317. Min Act: -0.1700
Data Index: 7501762 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3317. Min Range: -6.3317
Max Act: 5.8004. Min Act: -0.1700
Data Index: 7782786 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19