Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3057 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0129. Min Range: -5.0129
Max Act: 5.0129. Min Act: -0.1700
Data Index: 1347289 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0129. Min Range: -5.0129
Max Act: 4.9192. Min Act: -0.1700
Data Index: 2459030 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0129. Min Range: -5.0129
Max Act: 4.9192. Min Act: -0.1700
Data Index: 2443041 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0129. Min Range: -5.0129
Max Act: 4.8879. Min Act: -0.1700
Data Index: 4863025 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0129. Min Range: -5.0129
Max Act: 4.8567. Min Act: -0.1700
Data Index: 4430764 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0129. Min Range: -5.0129
Max Act: 4.8879. Min Act: -0.1700
Data Index: 7993079 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0129. Min Range: -5.0129
Max Act: 4.8254. Min Act: -0.1700
Data Index: 6881454 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0129. Min Range: -5.0129
Max Act: 4.8254. Min Act: -0.1700
Data Index: 2208493 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0129. Min Range: -5.0129
Max Act: 4.7942. Min Act: -0.1700
Data Index: 1156434 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0129. Min Range: -5.0129
Max Act: 4.7629. Min Act: -0.1700
Data Index: 8580623 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0129. Min Range: -5.0129
Max Act: 4.7317. Min Act: -0.1700
Data Index: 5965708 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0129. Min Range: -5.0129
Max Act: 4.7317. Min Act: -0.1700
Data Index: 8782662 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0129. Min Range: -5.0129
Max Act: 4.7317. Min Act: -0.1700
Data Index: 1280159 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0129. Min Range: -5.0129
Max Act: 4.7317. Min Act: -0.1700
Data Index: 4050359 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0129. Min Range: -5.0129
Max Act: 4.7004. Min Act: -0.1700
Data Index: 3474730 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0129. Min Range: -5.0129
Max Act: 4.7004. Min Act: -0.1700
Data Index: 2186463 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0129. Min Range: -5.0129
Max Act: 4.6692. Min Act: -0.1700
Data Index: 632748 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0129. Min Range: -5.0129
Max Act: 4.6692. Min Act: -0.1700
Data Index: 8304018 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0129. Min Range: -5.0129
Max Act: 4.6692. Min Act: -0.1700
Data Index: 3534060 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0129. Min Range: -5.0129
Max Act: 4.6692. Min Act: -0.1700
Data Index: 8135522 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19