Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3277 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.7071. Min Act: -0.1700
Data Index: 1192721 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.6758. Min Act: -0.1700
Data Index: 2632769 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.7071. Min Act: -0.1700
Data Index: 6578390 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.6758. Min Act: -0.1700
Data Index: 7169527 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.6446. Min Act: -0.1700
Data Index: 2627406 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.6446. Min Act: -0.1700
Data Index: 1192716 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.6446. Min Act: -0.1700
Data Index: 8556723 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.6446. Min Act: -0.1700
Data Index: 1192722 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.6446. Min Act: -0.1700
Data Index: 6135005 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.6133. Min Act: -0.1700
Data Index: 8747219 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.6133. Min Act: -0.1700
Data Index: 3590432 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.5821. Min Act: -0.1700
Data Index: 832321 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.6133. Min Act: -0.1700
Data Index: 6727773 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.5821. Min Act: -0.1700
Data Index: 5934658 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.5821. Min Act: -0.1700
Data Index: 1192720 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.5821. Min Act: -0.1700
Data Index: 2483360 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.5821. Min Act: -0.1700
Data Index: 5609271 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.5821. Min Act: -0.1700
Data Index: 2632770 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.5821. Min Act: -0.1700
Data Index: 3151657 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7071. Min Range: -4.7071
Max Act: 4.5821. Min Act: -0.1700
Data Index: 3956868 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19