Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 997 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.8826. Min Act: -0.1700
Data Index: 6947165 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.8826. Min Act: -0.1700
Data Index: 6456990 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.8044. Min Act: -0.1700
Data Index: 7475290 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.7575. Min Act: -0.1700
Data Index: 4927661 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.7575. Min Act: -0.1700
Data Index: 4550513 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.6949. Min Act: -0.1700
Data Index: 1563685 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.6793. Min Act: -0.1700
Data Index: 371973 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.6793. Min Act: -0.1700
Data Index: 1586832 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.6793. Min Act: -0.1700
Data Index: 3509236 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.6637. Min Act: -0.1700
Data Index: 5924618 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.6637. Min Act: -0.1700
Data Index: 7534613 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.6637. Min Act: -0.1700
Data Index: 1854137 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.6637. Min Act: -0.1700
Data Index: 4759711 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.6480. Min Act: -0.1700
Data Index: 2221697 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.6324. Min Act: -0.1700
Data Index: 5531050 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.6324. Min Act: -0.1700
Data Index: 4131958 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.6324. Min Act: -0.1700
Data Index: 6329092 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.6167. Min Act: -0.1700
Data Index: 1002094 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.6167. Min Act: -0.1700
Data Index: 4397869 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8826. Min Range: -3.8826
Max Act: 3.6011. Min Act: -0.1700
Data Index: 5773090 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19